dev-code-quality
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external codebase content, which presents a surface for indirect prompt injection if the scanned code contains instructions designed to manipulate the agent.
- Ingestion points: The agent reads the entire repository or specific directories to map structures, trace dependencies, and detect duplication (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential prompts embedded in the code (e.g., in comments or string literals).
- Capability inventory: The skill focus is on structural analysis and reporting findings; it does not explicitly define file-writing or network-sending capabilities, though it provides a refactoring plan that a user might ask the agent to execute.
- Sanitization: No evidence of sanitization or filtering of external code content is present in the skill instructions.
Audit Metadata