busirocket-core-conventions
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to interact with and refactor user-provided codebases, which creates a potential surface for indirect prompt injection if the ingested code contains malicious instructions.
- Ingestion points: User-provided source code files and repository structures (SKILL.md).
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within ingested files.
- Capability inventory: The agent is empowered to read, organize, and write code files to enforce boundaries and naming conventions across the project directory (core-boundaries-decision-tree.md).
- Sanitization: No specific measures for sanitizing external code content are provided for the refactoring process, although input validation is recommended for application route handlers.
Audit Metadata