registry / superclawd / 0.1.53
superclawd@0.1.53
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-aiSource confirms a powerful, user-invoked agent extension with transcript-derived remote memory and a Git hook. Its lifecycle behavior is disclosed and no concrete malicious chain occurs at npm installation.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
User runs superclawd after configuring credentials/workspace.
Impact
Session and tool-output content may be retained remotely; project Git hooks persist behavior after the CLI exits.
Mechanism
Claude hook-based transcript capture and remote memory persistence
AI rationale
Source confirms a powerful, user-invoked agent extension with transcript-derived remote memory and a Git hook. Its lifecycle behavior is disclosed and no concrete malicious chain occurs at npm installation.
Evidence
dist/index.jsdist/hook-helper.mjspackage.jsonREADME.md~/.superclawd/config.json~/.superclawd/sessions/<session>/plugin.git/hooks/post-commit
Network endpoints2
mcp-api.superclawd.comapi.superclawd.com
Decision evidence
public snapshotAI called this Suspicious at 90.0% confidence as Dangerous Capability with low false-positive risk.
Evidence for warning
- Runtime-generated Claude plugin captures session-end transcripts, including tool inputs/results.
- Captured content is condensed and posted as persistent SuperClawd memory.
- A user-invoked CLI run can install a project post-commit hook.
Evidence against
- No npm preinstall/install/postinstall hook; only prepublishOnly build.
- Behavior activates through the superclawd CLI, not package installation or import.
- README discloses Claude plugin loading and AI-captured memory.
Behavioral surface
ChildProcessEnvironmentVarsEvalFilesystemNetwork
HighEntropyStringsMinifiedUrlStrings
NoLicense
Source & flagged code
7 flaggeddist/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
Hardcoded Runtime Data Exfiltration
Source sends credentials or rich application records to a package-controlled external receiver enabled by default.
dist/index.jsView on unpkg · L22import { 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()?...
High
Findings
1 Critical5 High3 Medium7 Low
CriticalHardcoded Runtime Data Exfiltrationdist/index.js
HighChild Processdist/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
MediumNetwork
MediumEnvironment Vars
MediumStructural Risk Force Deep Review
LowNon Install Lifecycle Scripts
LowScripts Present
LowEvaldist/mcp-server.mjs
LowFilesystem
LowHigh Entropy Strings
Affected versions and remediation
This report applies to superclawd@0.1.53.
See all versions of superclawd for other recorded verdicts.
- Review the evidence and your use of superclawd@0.1.53 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.