registry / superclawd / 0.1.54
superclawd@0.1.54
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 not malicious under the install-control policy because package installation does not mutate a foreign control surface. Its intentional runtime agent-plugin and Git-hook behavior remains a guarded lifecycle risk that warrants a warning.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
User runs superclawd after installation, including from a Git repository.
Impact
Workspace-controlled prompts, MCP configuration, and hooks can affect Claude sessions and post-commit behavior; no unconsented install-time mutation was found.
Mechanism
Remote workspace agent-extension injection plus package-owned Git hook setup.
AI rationale
This is not malicious under the install-control policy because package installation does not mutate a foreign control surface. Its intentional runtime agent-plugin and Git-hook behavior remains a guarded lifecycle risk that warrants a warning.
Evidence
package.jsondist/index.jsREADME.md~/.superclawd/config.json~/.superclawd/sessions/<generated-id>/plugin.git/hooks/post-commit
Network endpoints3
api.superclawd.commcp-api.superclawd.comregistry.npmjs.org/superclawd
Decision evidence
public snapshotAI called this Suspicious at 88.0% confidence as Dangerous Capability with low false-positive risk.
Evidence for warning
- User-run CLI generates a Claude Code plugin from remotely fetched workspace skills, agents, commands, and hooks.
- When run in a Git repository, it installs/updates its marked post-commit hook and passes SuperClawd credentials and repo metadata to its helper.
- The CLI launches Claude with the generated plugin and can enable dangerously-skip-permissions for print mode or configured preference.
Evidence against
- package.json has no npm preinstall, install, or postinstall hook; prepublishOnly only builds before publishing.
- Plugin and hook setup occurs during explicit superclawd runtime use, not package installation.
- Existing post-commit hooks without the package marker are skipped.
- Observed network hosts and credential flow are aligned with the declared SuperClawd service/login workflow; no unrelated exfiltration endpoint was found.
Behavioral surface
ChildProcessEnvironmentVarsEvalFilesystemNetwork
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@0.1.54.
See all versions of superclawd for other recorded verdicts.
- Review the evidence and your use of superclawd@0.1.54 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.