Back to skill
Skillv0.1.0
ClawScan security
origin · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 18, 2026, 2:34 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is internally consistent and contains only small local shell scripts and documentation; it does not request credentials or perform network or file-exfiltrating actions, but the provided scripts are placeholders and do not implement full provenance functionality.
- Guidance
- This skill appears safe to inspect and run in a local or sandboxed environment: it contains two small bash scripts that only print status messages and timestamps and does not require any credentials. However, it is effectively a placeholder — it does not implement real lineage collection or backend integration. Before relying on it in production, review or extend the scripts to integrate with your provenance backends, and re-check future versions for added network calls or credential requirements. If you plan to run these scripts in a sensitive environment, run them in a sandbox first and confirm they behave as expected.
Review Dimensions
- Purpose & Capability
- noteThe name/description promise a data-provenance system, but the included artifacts are lightweight placeholder scripts that only print trace/audit messages and timestamps — they do not actually connect to backends, read pipeline metadata, or record lineage. This is likely a minimal/placeholder implementation rather than a fully functional provenance tool.
- Instruction Scope
- okSKILL.md instructs the agent (or user) only to run the included scripts (trace-lineage.sh, origin-info.sh). The instructions do not ask the agent to read unrelated files, access environment variables, or transmit data externally.
- Install Mechanism
- okThere is no install spec (instruction-only with small script files). No downloads or external package installs are performed, so nothing arbitrary is written to disk beyond the included scripts.
- Credentials
- okThe skill requests no environment variables, credentials, or config paths. The claw.json lists an "exec" permission to run the scripts, which is appropriate for a script-based skill.
- Persistence & Privilege
- okalways is false and the skill does not modify other skills or system-wide configuration. It does not request persistent presence or elevated privileges.