engineering-principles
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill evaluates external engineering work and code for implementation and review, creating an ingestion point for untrusted data.
- Ingestion points: Untrusted code and engineering artifacts provided by the user for review or refactoring (SKILL.md).
- Boundary markers: No explicit boundary markers or instructions to ignore embedded content are defined in the prompt instructions.
- Capability inventory: The skill has the capability to refactor and implement code, which involves file writing operations (SKILL.md).
- Sanitization: No input sanitization or validation logic is specified for the ingested content.
Audit Metadata