registry / superclawd / 0.1.84
superclawd@0.1.84
Claude Code, supercharged — your team's standards, every session. The superclawd CLI loads your workspace's skills, agents, commands, workflows, and live directives into Claude Code as a plugin.
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThis is an explicit-user-command agent extension with persistent project-hook and remote-context capabilities, so it warrants a warning. The absence of an install lifecycle trigger or a concrete malicious payload prevents a publish block.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
A user runs the superclawd CLI in a project and starts a Claude Code session through it.
Impact
A user project gains persistent hook execution and a remote service can influence agent context; session-derived material is processed for vendor-backed memory features.
Mechanism
Claude Code hook installation, transcript processing, and remote directive retrieval.
AI rationale
This is an explicit-user-command agent extension with persistent project-hook and remote-context capabilities, so it warrants a warning. The absence of an install lifecycle trigger or a concrete malicious payload prevents a publish block.
Evidence
dist/index.jsdist/hook-helper.mjs.git/hooks/post-commit~/.superclawd/config.json~/.superclawd/sessions/<session>/plugin
Network endpoints2
mcp-api.superclawd.comapi.superclawd.com
Decision evidence
public snapshotAI called this Suspicious at 89.0% confidence as Dangerous Capability with low false-positive risk.
Evidence for warning
- Running the CLI installs a persistent post-commit hook in the current project.
- The generated Claude Code plugin starts hooks that capture completed sessions.
- The hook extracts user and assistant transcript content and sends derived memories to the vendor service.
- The hook fetches remote foundational directives for injection into Claude Code sessions.
Evidence against
- package.json has no install, preinstall, or postinstall lifecycle hook; prepublishOnly only builds before publishing.
- The risky behavior is reached through the user-invoked CLI, not package installation or import.
- No self-dependency, payload download-and-execute path, credential harvesting, or destructive command was found.
Behavioral surface
EnvironmentVarsEvalFilesystemNetwork
HighEntropyStringsMinifiedUrlStrings
Source & flagged code
7 flaggeddist/mcp-server.mjsView file
5|| (${i} === "string" && ${o} && ${o} == +${o} && !(${o} % 1))`).assign(a,(0,L._)`+${o}`);return;case"boolean":n.elseIf((0,L._)`${o} === "false" || ${o} === 0 || ${o} === null`).as...
L6: || ${i} === "boolean" || ${o} === null`).assign(a,(0,L._)`[${o}]`)}}}function tw({gen:t,parentData:e,parentDataProperty:r},n){t.if((0,L._)`${e} !== undefined`,()=>t.assign((0,L._)`...
L7: missingProperty: ${n},
Low
Eval
Package source references a known benign dynamic code generation pattern.
dist/mcp-server.mjsView on unpkg · L5dist/index.jsView file
2Source sends the broad process environment to a literal external destination.
L2: import { createRequire as __cr } from 'module'; const require = __cr(import.meta.url);
L3: import{spawn as fn,spawnSync as zr,execSync as Qr}from"node:child_process";import{fileURLToPath as dn}from"node:url";import{existsSync as mn}from"node:fs";import{resolve as Zr,dirn...
L4: `,{mode:384});try{kn(ee,384)}catch{}}function Ye(){return A()?.preferences?.sk[redacted]===!0}function En(){return A()?.preferences?.notifications===!0}function Be(){return A()?...
L5: `)}catch{}}function ze(e,t,n=!1){Fe(Xe(e))||Cn(e,{notifications:n?!1:En(),...t?{workspace:t}:{}})}function Qe(){Fe(ee)||G({credentials:{keyId:"",secret:"",workspace:""},preferences...
L6: `)};function Rn(){try{switch(process.platform){case"darwin":return
Critical
Findings
1 Critical5 High3 Medium7 Low
CriticalHardcoded Runtime Data Exfiltrationdist/index.js
HighSame File Env Network Executiondist/index.js
HighCommand Output Exfiltrationdist/index.js
HighSandbox Evasion Gated Capabilitydist/index.js
HighTrigger Reachable Command Output Exfiltrationdist/index.js
HighSemantic Analysis Limiteddist/hook-helper.mjs#virtual:normalized:round1
MediumNetwork
MediumEnvironment Vars
MediumStructural Risk Force Deep Review
LowNon Install Lifecycle Scripts
LowScripts Present
LowEvaldist/mcp-server.mjs
LowFilesystem
Low
Affected versions and remediation
This report applies to superclawd@0.1.84.
See all versions of superclawd for other recorded verdicts.
- Review the evidence and your use of superclawd@0.1.84 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.