refactor-understand

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Node.js scripts to perform repository diagnostics. It calls scripts/checklist.mjs and a suite-specific script located at ~/.claude/skills/refactor-chain/scripts/diagnose.mjs. These operations are limited to gathering information about the target directory and are consistent with the skill's stated purpose.
  • [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by ingesting untrusted data from target repositories.
  • Ingestion points: The agent reads manifest files (e.g., package.json, pom.xml), lockfiles, CI configurations (.github/workflows), and directory structures from the target codebase.
  • Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious embedded content within these files.
  • Capability inventory: The skill's capabilities are restricted to read-only diagnostics and the execution of the author's own utility scripts. It does not have network access or file-write permissions.
  • Sanitization: There is no explicit sanitization described for the content of the ingested files; however, the data is primarily used to populate a structured Project Profile template.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 01:02 AM
Security Audit — agent-trust-hub — refactor-understand