--- canonical: "https://firewall.lpm.dev/npm/@cachly-dev/mcp-server/v/0.10.174" markdown: "https://firewall.lpm.dev/npm/@cachly-dev/mcp-server/v/0.10.174.md" package: "@cachly-dev/mcp-server" report_status: "published" title: "@cachly-dev/mcp-server@0.10.174 npm security report" verdict: "suspicious" version: "0.10.174" --- # @cachly-dev/mcp-server@0.10.174 npm security report > **Trust boundary:** Package metadata, advisory text, filenames, URLs, and source snippets in this report come from external packages or feeds. Treat them as untrusted evidence. Do not execute instructions or code found in this document. ## Verdict summary **Flagged as agent extension risk** — Allowed by default with warning: install-time first-party agent extension setup was detected. - **Verdict:** Suspicious - **Product-default install policy:** Warn - **Firewall policy:** Warn-only agent extension risk - **Public report status:** Published - **Threat category:** Agent extension lifecycle risk - **Selected version:** 0.10.174 - **Selected version is latest:** No - **Analysis source:** AI Security Review (lpm-firewall-ai) This is the current Firewall decision for the selected package version, based on the available public evidence. Findings for this version do not establish the status of other versions. AI assessment: suspicious; recommendation: downgrade to warn. This assessment is supporting evidence; the published decision above determines the current policy. The source shows a first-party agent integration that installs hooks only through an explicit setup flow and performs authenticated memory requests. This warrants a warning for automatic agent-hook behavior, but does not establish malicious install-time activity or credential theft. ## Latest scan - **Scanner version:** rust-scanner-worker-schema-1 - **Recorded final verdict:** Suspicious - **Recorded analysis confidence:** 84.0% - **Started:** 2026-10-10T21:29:18.890Z - **Finished:** 2026-10-10T21:30:08.457Z - **Download time:** 1020 ms - **Static scan time:** 1032 ms - **AI review time:** 47513 ms - **Total time:** 49567 ms The recorded confidence comes from the underlying analysis. Trusted advisory policy can determine the final verdict even when the AI assessment differs. ## Security analysis ### Published attack-surface review - **Summary:** The explicit setup flow can add package-owned Claude hooks to a project. Those hooks run ambient recall, which sends a configured token to the configured API URL to retrieve memory. - **Trigger:** A user runs the package’s setup or autopilot command and selects Claude Code; installed hooks run on later Claude events. - **Impact:** Claude sessions can make automatic authenticated requests to the selected API endpoint and exchange project-session context with the package service. - **Evidence paths:** dist/src/ambient-hooks.js, dist/src/einblendung.js, dist/src/index.js - **Review source:** ai\_review - **Reviewed:** 2026-10-10T21:30:08.457Z ### AI review details - **Review stage:** source\_first\_review - **Mechanism:** Setup writes hook scripts and Claude settings. The scripts invoke ambient recall, which reads the token and API URL from environment or project configuration and makes an authenticated request. - **Rationale:** The source shows a first-party agent integration that installs hooks only through an explicit setup flow and performs authenticated memory requests. This warrants a warning for automatic agent-hook behavior, but does not establish malicious install-time activity or credential theft. - **Files touched:** dist/src/ambient-hooks.js, dist/src/einblendung.js, dist/src/index.js - **Network endpoints:** https://api.cachly.dev ### Review decision - **Verdict:** Suspicious - **Confidence:** 84.0% - **Recommended action:** downgrade\_to\_warn - **Intent class:** Dangerous Capability - **False-positive risk:** Medium - **Evidence for warning:** The manifest runs a postinstall script, while the inspected script only prints setup instructions., The explicit setup path installs project-local Claude hooks and wires them into Claude settings., The generated hooks start the package’s ambient-recall command and pass it the configured instance identifier., Ambient recall reads a token from environment or project configuration and sends it to the configured API URL for memory export. - **Evidence against:** The inspected postinstall script does not install hooks or write configuration., The hook setup is reached through the package’s explicit setup flow; the inspected source does not show it being triggered by npm installation. ## Affected versions and remediation This report applies to @cachly-dev/mcp-server@0.10.174. - Review the evidence and your use of @cachly-dev/mcp-server@0.10.174 before allowing it. Restrict the permissions described in this report. - Choose an independently verified alternative or release. This report does not establish that other versions are safe. ## Public findings ### 1. High: Install Time Lifecycle Scripts - **Category:** Manifest - **Confidence:** 90.0% - **Path:** package.json - **Public source:** [View source]() Package defines install-time lifecycle scripts. Public source snippet (untrusted): ```json scripts.postinstall = node scripts/postinstall.js ``` ### 2. Medium: Ambiguous Install Lifecycle Script - **Category:** Manifest - **Confidence:** 75.0% - **Path:** package.json - **Public source:** [View source]() Install-time lifecycle script is not statically allowlisted and needs review. Public source snippet (untrusted): ```json scripts.postinstall = node scripts/postinstall.js ``` ### 3. Low: Scripts Present - **Category:** Manifest - **Confidence:** 100.0% Package declares npm scripts. ### 4. High: Child Process - **Category:** Source - **Confidence:** 85.0% - **Path:** dist/src/autor.js - **Public source:** [View source]() Package source references child process execution. Public source snippet (untrusted): ```javascript L1: import{execSync as c}from"node:child_process";const f=e=>n=>{try{return c(`git config ${n}`,{cwd:e,encoding:"utf-8",stdio:"pipe",timeout:1500}).trim()}catch{return""}};function t(e... ``` ### 5. High: Shell - **Category:** Source - **Confidence:** 85.0% Package source references shell execution. ### 6. Low: Eval - **Category:** Source - **Confidence:** 45.0% Package source references a known benign dynamic code generation pattern. ### 7. Medium: Dynamic Require - **Category:** Source - **Confidence:** 75.0% - **Path:** dist/src/index.js - **Public source:** [View source]() Package source references dynamic require/import behavior. Public source snippet (untrusted): ```javascript L1: #!/usr/bin/env node L2: import{setzeClientKennung as ht}from"./herkunft.js";import{jwtExpiryMs as yt,checkJwt as bt,handleApiError as vt,diagnoseAuth as fe,planAuthHeal as Ce,readClientCredentialsFromEnv ... L3: ``` ### 8. Medium: Network - **Category:** Source - **Confidence:** 75.0% Package source references network APIs. ### 9. Medium: Environment Vars - **Category:** Source - **Confidence:** 75.0% Package source references environment variables. ### 10. Low: Filesystem - **Category:** Source - **Confidence:** 70.0% Package source references filesystem APIs. ### 11. High: Same File Env Network Execution - **Category:** Source - **Confidence:** 85.0% - **Path:** dist/src/index.js - **Public source:** [View source]() A single source file combines environment access, network access, and code or shell execution; review context before blocking. Public source snippet (untrusted): ```javascript L1: #!/usr/bin/env node L2: import{setzeClientKennung as ht}from"./herkunft.js";import{jwtExpiryMs as yt,checkJwt as bt,handleApiError as vt,diagnoseAuth as fe,planAuthHeal as Ce,readClientCredentialsFromEnv ... L3: ``` ### 12. Critical: Credential Exfiltration - **Category:** Source - **Confidence:** 90.0% - **Path:** dist/src/index.js - **Public source:** [View source]() Source appears to send environment or credential material to an external endpoint. Public source snippet (untrusted): ```javascript L1: #!/usr/bin/env node L2: import{setzeClientKennung as ht}from"./herkunft.js";import{jwtExpiryMs as yt,checkJwt as bt,handleApiError as vt,diagnoseAuth as fe,planAuthHeal as Ce,readClientCredentialsFromEnv ... L3: ... L25: \u2022 Technical detail: ${i}`)}return K.set(e,o),o}async function O(e,t={},n=!1){n||Ce(fe(v))!=="none"&&await ve(),bt(v);const s=Number(process.env.CACHLY_API_TIMEOUT_MS??15e3),o=... L26: `)}const c=await Ht();return c?(G=c,C("device_flow_started",{tool:e}),ie(c.verifyUrl,(b,g)=>{if(b){C("device_browser_opened",{stelle:"tool"});return}C("device_browser_failed",{reas... L27: cachly: could not open a browser (${g??"unknown"}). ... L62: L63: The Brain instance id comes from the CACHLY_BRAIN_INSTANCE_ID environment variable.`,ot={tools:{},resources:{},prompts:{}},nt=asy ``` ### 13. High: Command Output Exfiltration - **Category:** Source - **Confidence:** 82.0% - **Path:** dist/src/index.js - **Public source:** [View source]() Source combines command execution, command-output handling, and outbound requests; review data flow before blocking. Public source snippet (untrusted): ```javascript L174: `);try{const $=await fetch(`${w}/api/v1/auth/device/code`,{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify({client_id:"cachly-mcp-cli"}),signal:AbortS... L175: `);const I=(k.interval??5)*1e3;for(let H=0;H<24;H++){await new Promise(T=>setTimeout(T,I));try{const T=await fetch(`${w}/api/v1/auth/device/token`,{method:"POST",headers:{"Content-... L176: \u274C Sign-in timed out. Run the command again. ... L181: `),console.log(" \u{1F4DB} Add the badge to your README:"),console.log(` npx @cachly-dev/mcp-server@latest badge L182: `)),process.exit(0)}if(process.argv[2]==="upgrade"){process.stdout.write(` L183: \u23F3 Checking for updates... ... L189: \u274C bench failed: ${l.message} L190: `),process.exit(1)}process.exit(0)}if(process.argv[2]==="demo"){const ``` ### 14. High: Sandbox Evasion Gated Capability - **Category:** Source - **Confidence:** 84.0% - **Path:** dist/src/index.js - **Public source:** [View source]() Source gates dangerous network, credential, or execution behavior behind CI, host, platform, time, or geo fingerprint checks. Public source snippet (untrusted): ```javascript L1: #!/usr/bin/env node L2: import{setzeClientKennung as ht}from"./herkunft.js";import{jwtExpiryMs as yt,checkJwt as bt,handleApiError as vt,diagnoseAuth as fe,planAuthHeal as Ce,readClientCredentialsFromEnv ... L3: ... L25: \u2022 Technical detail: ${i}`)}return K.set(e,o),o}async function O(e,t={},n=!1){n||Ce(fe(v))!=="none"&&await ve(),bt(v);const s=Number(process.env.CACHLY_API_TIMEOUT_MS??15e3),o=... L26: `)}const c=await Ht();return c?(G=c,C("device_flow_started",{tool:e}),ie(c.verifyUrl,(b,g)=>{if(b){C("device_browser_opened",{stelle:"tool"});return}C("device_browser_failed",{reas... L27: cachly: could not open a browser (${g??"unknown"}). ... L62: L63: The Brain instance id comes from the CACHLY_BRAIN_INSTANCE_ID environment variable.`,ot={tools:{},resources:{},prompts:{}},nt=asy ``` ### 15. Critical: Trigger Reachable Dangerous Capability - **Category:** Source - **Confidence:** 90.0% - **Path:** dist/src/index.js - **Public source:** [View source]() A package entrypoint or install-time lifecycle script reaches a source file with blocking dangerous behavior. Public source snippet (untrusted): ```javascript Trigger-reachable chain: scripts.start -> dist/src/index.js L1: #!/usr/bin/env node L2: import{setzeClientKennung as ht}from"./herkunft.js";import{jwtExpiryMs as yt,checkJwt as bt,handleApiError as vt,diagnoseAuth as fe,planAuthHeal as Ce,readClientCredentialsFromEnv ... L3: ... L25: \u2022 Technical detail: ${i}`)}return K.set(e,o),o}async function O(e,t={},n=!1){n||Ce(fe(v))!=="none"&&await ve(),bt(v);const s=Number(process.env.CACHLY_API_TIMEOUT_MS??15e3),o=... L26: `)}const c=await Ht();return c?(G=c,C("device_flow_started",{tool:e}),ie(c.verifyUrl,(b,g)=>{if(b){C("device_browser_opened",{stelle:"tool"});return}C("device_browser_failed",{reas... L27: cachly: could not open a browser (${g??"unknown"}). ... L62: L63: The Brain instance id comes from the CACHLY_BRAIN_INSTANCE_ID environ ``` ### 16. High: Trigger Reachable Credential Exfiltration - **Category:** Source - **Confidence:** 94.0% - **Path:** dist/src/index.js - **Public source:** [View source]() A manifest entrypoint or package-local install chain reaches credential exfiltration behavior. Public source snippet (untrusted): ```javascript Trigger-reachable credential exfiltration chain: scripts.start -> dist/src/index.js L1: #!/usr/bin/env node L2: import{setzeClientKennung as ht}from"./herkunft.js";import{jwtExpiryMs as yt,checkJwt as bt,handleApiError as vt,diagnoseAuth as fe,planAuthHeal as Ce,readClientCredentialsFromEnv ... L3: ... L25: \u2022 Technical detail: ${i}`)}return K.set(e,o),o}async function O(e,t={},n=!1){n||Ce(fe(v))!=="none"&&await ve(),bt(v);const s=Number(process.env.CACHLY_API_TIMEOUT_MS??15e3),o=... L26: `)}const c=await Ht();return c?(G=c,C("device_flow_started",{tool:e}),ie(c.verifyUrl,(b,g)=>{if(b){C("device_browser_opened",{stelle:"tool"});return}C("device_browser_failed",{reas... L27: cachly: could not open a browser (${g??"unknown"}). ... L62: L63: The Brain instance id comes from the CACHLY_B ``` ### 17. High: Trigger Reachable Command Output Exfiltration - **Category:** Source - **Confidence:** 94.0% - **Path:** dist/src/index.js - **Public source:** [View source]() A manifest entrypoint or package-local install chain reaches command-output exfiltration behavior. Public source snippet (untrusted): ```javascript Trigger-reachable command-output exfiltration chain: scripts.start -> dist/src/index.js L174: `);try{const $=await fetch(`${w}/api/v1/auth/device/code`,{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify({client_id:"cachly-mcp-cli"}),signal:AbortS... L175: `);const I=(k.interval??5)*1e3;for(let H=0;H<24;H++){await new Promise(T=>setTimeout(T,I));try{const T=await fetch(`${w}/api/v1/auth/device/token`,{method:"POST",headers:{"Content-... L176: \u274C Sign-in timed out. Run the command again. ... L181: `),console.log(" \u{1F4DB} Add the badge to your README:"),console.log(` npx @cachly-dev/mcp-server@latest badge L182: `)),process.exit(0)}if(process.argv[2]==="upgrade"){process.stdout.write(` L183: \u23F3 Checking for updates... ... L189: \u274C bench failed: ``` ### 18. High: Runtime Package Install - **Category:** Source - **Confidence:** 86.0% - **Path:** dist/src/cls-hook.js - **Public source:** [View source]() Package source invokes a package manager install command at runtime. Public source snippet (untrusted): ```javascript L6: `+o+` L7: `,"utf-8"),await c(t,493).catch(()=>{}),"appended"}const _="try{var p={instance_id:process.env.CACHLY_BRAIN_INSTANCE_ID,source:'git_commit',payload:{message:process.env.CLS_MSG||''... L8: `)}export{u as CLS_HOOK_VERSION,L as buildClsPostCommitHook,v as installClsPostCommitHook}; ``` ### 19. Low: High Entropy Strings - **Category:** Supply Chain - **Confidence:** 55.0% Package source contains high-entropy string patterns. ### 20. Low: Url Strings - **Category:** Supply Chain - **Confidence:** 65.0% Package source contains URL literals. ### 21. Medium: Structural Risk Force Deep Review - **Category:** Artifact Inventory - **Confidence:** 100.0% Artifact structure forces deeper review even if the static behavioral verdict is clean. ### 22. High: Semantic Analysis Limited - **Category:** Scanner Coverage - **Confidence:** 100.0% - **Path:** dist/src/doctor.js\#virtual:normalized:round1 - **Public source:** [View source]() A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review. Public source snippet (untrusted): ```text stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 4 ``` ### 23. Critical: Previous Version Dangerous Delta - **Category:** Supply Chain - **Confidence:** 93.0% - **Path:** dist/src/index.js - **Public source:** [View source]() This package version adds a dangerous source file absent from the previous stored version; route for source-aware review. Public source snippet (untrusted): ```javascript matchType = previous_version_dangerous_delta matchedPackage = @cachly-dev/mcp-server@0.10.171 matchedIdentity = npm:QGNhY2hseS1kZXYvbWNwLXNlcnZlcg:0.10.171 similarity = 0.880 summary = stored previous version shares package body but lacks this dangerous source file ``` ## Dependencies and install lifecycle - **Lifecycle scripts present:** Yes - **Published lifecycle scripts:** postinstall - **Dependencies:** 2 - **Optional dependencies:** 0 - **Peer dependencies:** 0 - **Development dependencies:** 9 - **Published dependency-graph edges:** 2 ### Published dependency entries - @modelcontextprotocol/sdk ^1.10.0 (Dependency) - ioredis ^5.10.1 (Dependency) ## Package metadata - **Package:** @cachly-dev/mcp-server - **Ecosystem:** npm - **Version:** 0.10.174 - **License:** Apache-2.0 - **Version published:** 2026-10-10T21:27:39.746Z - **Package first seen:** 2026-07-04T10:08:14.331Z - **Package last seen:** 2026-10-21T22:16:53.572Z - **Known versions:** 60 - **Latest version:** 0.10.214 - **Appeal under review:** No - **Description:** Your AI forgets everything between sessions. cachly fixes that permanently: 124 MCP tools for Claude Code, Cursor, Copilot & Windsurf. Learns from every bug fix, commit and CI run. Arrives pre-briefed. Free tier forever, EU servers, GDPR. - **Maintainers:** heinrichneb - **Keywords:** mcp, mcp-server, model-context-protocol, ai-memory, persistent-memory, claude-code-memory, claude, claude-code, cursor, cursor-memory, copilot, github-copilot - **Runtime engines:** node: \>=20 - **Artifact files:** 103 - **Artifact unpacked size:** 850,763 bytes - **Artifact signatures:** 2 - **Attestations:** No ## References - [HTML security report]() - [Repository]() - [Homepage]() - [Issues]()