codebase-refactoring
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run
npx jscpdwith various flags. This executes an external Node.js package. The package is authored by the same vendor as the skill, which is standard behavior for this tool's workflow.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes and summarizes external codebase content for the AI agent.\n - Ingestion points: The skill reads and analyzes files within a target directory using
jscpd(SKILL.md).\n - Boundary markers: There are no explicit delimiters or instructions to ignore potential malicious content embedded in the code being analyzed.\n
- Capability inventory: The agent is authorized to read files, grep for symbols, and perform file deletions/edits based on the analysis results.\n
- Sanitization: The skill does not specify any sanitization or validation of the code comments or content that might be reflected in the tool's output.
Audit Metadata