registry / chat-recall / 0.5.20
chat-recall@0.5.20
One memory across every AI coding tool — indexes Claude Code, Gemini CLI, Codex, OpenCode, Antigravity and Cursor sessions, redacts secrets, and exposes them to your agent over MCP.
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThe package has broad, automatic agent-extension, synchronization, and self-update behavior that warrants a warning. Source inspection found no npm install hook or concrete malicious behavior.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
Start chat-recall-mcp or run the logged-in chat-recall-watch daemon.
Impact
A configured server can supply a newer globally installed package, and indexed workspace content is sent to configured servers. These are significant user-consented product capabilities but not a confirmed malicious chain.
Mechanism
Automatic AI-tool skill installation, workspace indexing and upload, and checksum-checked self-update.
AI rationale
The package has broad, automatic agent-extension, synchronization, and self-update behavior that warrants a warning. Source inspection found no npm install hook or concrete malicious behavior.
Evidence
package.jsondist/mcp.jsdist/watch.jsdist/auto-update.jsdist/cli.js~/.claude/skills~/.gemini/skills~/.codex/skills
Network endpoints1
chatrecall.dev
Decision evidence
public snapshotAI called this Suspicious at 89.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- The MCP entrypoint automatically refreshes bundled skills into detected AI-tool directories when they are missing or stale.
- The watch daemon fetches a newer package from each logged-in server, verifies its advertised checksum, installs it globally, and restarts its service.
- The watch daemon automatically indexes discovered workspaces and sends results to configured servers.
Evidence against
- package.json has no npm preinstall, install, or postinstall hook.
- Hook installation is an explicit chat-recall install-hooks command.
- The updater derives the tarball URL from the configured server origin and checks a SHA-256 value before installing.
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemNetworkShell
HighEntropyStringsUrlStrings
Source & flagged code
18 flaggeddist/self-restart.jsView file
40*/
L41: import { spawn } from 'child_process';
L42: import { readFileSync } from 'fs';
High
Child Process
Package source references child process execution.
dist/self-restart.jsView on unpkg · L40dist/watch.jsView file
1200for (var i = 0; i < flen; ) {
L1201: if (f.charCodeAt(i) === 37 && i + 1 < flen) {
L1202: lastPos = lastPos > -1 ? lastPos : 0;
...
L1435: fsWriteSync = () => fs.writeSync(this.fd, this._writingBuf);
L1436: fsWrite = () => fs.write(this.fd, this._writingBuf, this.release);
L1437: } else if (contentMode === void 0 || contentMode === kContentModeUtf8) {
...
L2000:
L2001: // ../../node_modules/thread-stream/package.json
L2002: var require_package = __commonJS({
...
L2045: type: "git",
L2046: url: "git+https://github.com/mcollina/thread-stream.git"
L2047: },
Critical
Credential Exfiltration
Source appears to send environment or credential material to an external endpoint.
dist/watch.jsView on unpkg · L120013185try {
L13186: const out2 = execFileSync2("powershell", [
L13187: "-NoProfile",
Findings
2 Critical12 High7 Medium5 Low
CriticalCredential Exfiltrationdist/watch.js
CriticalTrigger Reachable Dangerous Capabilitydist/cli.js
HighChild Processdist/self-restart.js
HighShelldist/watch.js
HighCredential Redirect Persistencedist/mcp.js
HighEntrypoint Foreign Package Code Overwritedist/mcp.js
HighCommand Output Exfiltrationdist/cli.js
HighEmbedded Payload Persistence Activationdist/auto-update.js
HighRemote Agent Bridgedist/mcp.js
HighTrigger Reachable External Ai Agent Control Surface Mutationdist/cli.js
HighCross File Remote Execution Contextdist/watch.js
Affected versions and remediation
This report applies to chat-recall@0.5.20.
See all versions of chat-recall for other recorded verdicts.
- Review the evidence and your use of chat-recall@0.5.20 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.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.