registry / superclawd / 0.1.42
superclawd@0.1.42
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 3mo ago · by lpm-firewall-aiNo concrete malicious install-time behavior, stealth persistence, or unconsented foreign control-surface mutation was found. The package nevertheless warrants a warning because it installs active per-session Claude hooks and handles transcript-derived memory via its service.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
Explicit superclawd CLI launch after authentication
Impact
A trusted workspace can influence Claude sessions and receive configured memory content; no install-time or broad foreign-agent mutation is present.
Mechanism
Temporary Claude plugin and transcript-backed remote memory integration
AI rationale
No concrete malicious install-time behavior, stealth persistence, or unconsented foreign control-surface mutation was found. The package nevertheless warrants a warning because it installs active per-session Claude hooks and handles transcript-derived memory via its service.
Evidence
package.jsondist/index.jsdist/hook-helper.mjsdist/mcp-server.mjsREADME.md~/.superclawd/config.json~/.superclawd/sessions/<session>/plugin/.claude-plugin/plugin.json~/.superclawd/sessions/<session>/plugin/hooks/hooks.json
Network endpoints3
mcp-api.superclawd.comapi.superclawd.comregistry.npmjs.org
Decision evidence
public snapshotAI called this Suspicious at 90.0% confidence as Dangerous Capability with low false-positive risk.
Evidence for warning
- User-invoked CLI creates a per-session Claude Code plugin with hooks and MCP configuration.
- The generated plugin passes SuperClawd credentials to its MCP server and retrieves remote workspace content.
- Hook helper reads Claude session transcripts for memory capture; the package offers remote memory APIs.
Evidence against
- No npm preinstall, install, or postinstall hook; only prepublishOnly runs a build.
- Plugin files are created below the package-owned ~/.superclawd/sessions area and removed after the run.
- Network, credentials, workspace injection, and memory features match the documented authenticated CLI purpose; no covert foreign-agent mutation found.
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@0.1.42.
See all versions of superclawd for other recorded verdicts.
- Review the evidence and your use of superclawd@0.1.42 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.