superclawd@0.1.107
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 3d ago · by lpm-firewall-aiThe runtime sends a project-derived Git remote value to the package’s own service by default, which meets the rule for suspicious identifying telemetry. The source does not establish a concrete credential theft chain or an install-time attack.
Static reason
High-risk behavior combination matched malicious policy.; source matched previously finalized malicious package; routed for review; source fingerprint signature matched known malicious package; routed for review
Trigger
Running the CLI after Claude Code is available.
Impact
The service receives project-identifying data; an origin URL could also contain embedded credentials.
Mechanism
It reads the origin Git remote (or derives a directory fingerprint), stores the value in an environment variable, and includes it in the catalog request.
AI rationale
The runtime sends a project-derived Git remote value to the package’s own service by default, which meets the rule for suspicious identifying telemetry. The source does not establish a concrete credential theft chain or an install-time attack.
Evidence
dist/index.js
Network endpoints1
mcp-api.superclawd.com/api/prompt/catalog
Decision evidence
public snapshotAI called this Suspicious at 88.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- On normal CLI startup, the package derives `SUPERCLAWD_REPO_FINGERPRINT` from the origin Git remote, falling back to a directory fingerprint.
- The CLI sends that fingerprint with a catalog request to the package service; a Git remote can identify the project and may contain embedded credentials.
Evidence against
- The manifest has no install, preinstall, or postinstall hook; `prepublishOnly` only runs the build.
- The flagged device-login requests send a machine ID and hostname to the package’s own API as part of an explicit login flow.
Behavioral surface
ChildProcessEnvironmentVarsEvalFilesystemNetworkShell
HighEntropyStringsMinifiedUrlStrings
NoLicense
Source & flagged code
13 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: var Xe=["opus","fable","sonnet","haiku"],Un={opus:"claude-opus-5-5",fable:"claude-fable-5-1",sonnet:"claude-sonnet-5-5",haiku:"claude-haiku-5-5"},Wn=/^claude-(opus|fable|sonnet|hai...
L4: `,{mode:384});try{Bn(se,384)}catch{}}function nt(){return L()?.preferences?.sk[redacted]===!0}function qn(){return L()?.preferences?.notifications===!0}function rt(){return L()?...
L5: `)}catch{}}function ct(e,t,n=!1){et(lt(e))||Jn(e,{notifications:n?!1:qn(),...t?{workspace:t}:{}})}function ut(){et(se)||Y({credentials:{keyId:"",secret:"",workspace:""},preferences...
L6: `)};function Vn(){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: var Xe=["opus","fable","sonnet","haiku"],Un={opus:"claude-opus-5-5",fable:"claude-fable-5-1",sonnet:"claude-sonnet-5-5",haiku:"claude-haiku-5-5"},Wn=/^claude-(opus|fable|sonnet|hai...
L4: `,{mode:384});try{Bn(se,384)}catch{}}function nt(){return L()?.preferences?.sk[redacted]===!0}function qn(){return L()?.preferences?.notifications===!0}function rt(){return L()?...
High
Findings
1 Critical11 High3 Medium7 Low
CriticalHardcoded Runtime Data Exfiltrationdist/index.js
HighChild Processdist/index.js
HighShelldist/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
HighKnown Malware Source Similaritydist/hook-helper.mjs
HighKnown Malware Source Similaritydist/index.js
HighKnown Malware Source Similaritydist/mcp-server.mjs
Affected versions and remediation
This report applies to superclawd@0.1.107.
See all versions of superclawd for other recorded verdicts.
- Review the evidence and your use of superclawd@0.1.107 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.