registry / superclawd / 0.1.36
superclawd@0.1.36
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-aiSource inspection found an explicit, authenticated agent-extension workflow with memory synchronization and a Git hook, but no install-time execution or covert malicious chain. Warn for lifecycle and data-handling risk rather than block as malware.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
User runs superclawd after authenticating and launching a Claude Code session; subsequent session events or commits activate hooks.
Impact
Transcript-derived memory and repository metadata may be sent to the configured SuperClawd service; a project Git hook persists after the CLI run.
Mechanism
Claude extension lifecycle hooks and authenticated memory synchronization.
AI rationale
Source inspection found an explicit, authenticated agent-extension workflow with memory synchronization and a Git hook, but no install-time execution or covert malicious chain. Warn for lifecycle and data-handling risk rather than block as malware.
Evidence
package.jsondist/index.jsdist/hook-helper.mjsREADME.md.git/hooks/post-commit~/.superclawd/config.json~/.superclawd/sessions/<id>/plugin
Network endpoints3
mcp-api.superclawd.comapi.superclawd.comregistry.npmjs.org/superclawd
Decision evidence
public snapshotAI called this Suspicious at 86.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- User-run CLI generates Claude hooks that trigger capture on Stop and SessionEnd.
- The hook helper posts learned-memory content to the authenticated SuperClawd API.
- Each CLI run can install a managed Git post-commit hook in the current repository.
- Package is an executable CLI, not an install-time payload.
Evidence against
- package.json has only prepublishOnly; no preinstall/install/postinstall hook.
- Network use, login, workspace selection, and memory capture align with the documented CLI product.
- No source evidence of stealthy install-time execution, remote code loading, credential theft, or destructive commands.
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@0.1.36.
See all versions of superclawd for other recorded verdicts.
- Review the evidence and your use of superclawd@0.1.36 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.