readme
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from project files (e.g., package.json, composer.json) which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill reads package.json, composer.json, and other project files.
- Boundary markers: No specific boundary markers or 'ignore embedded instructions' warnings are provided.
- Capability inventory: The skill identifies features and dependencies to generate text; no network operations, subprocess executions, or file-writing capabilities were identified in the instructions.
- Sanitization: There is no evidence of input validation or sanitization for the content read from files.
Audit Metadata