refactor
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes existing codebases, creating a surface for indirect prompt injection where malicious instructions embedded in source files could influence the agent's behavior.
- Ingestion points: Workflow step 1 in
SKILL.mdrequires inspecting available files and repository instructions. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands in the source material are present.
- Capability inventory: The skill can execute
sandbase_run(external API calls), run tests, and perform build/static checks. - Sanitization: No explicit sanitization or filtering of codebase content is mentioned before processing.
Audit Metadata