verification-guide
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to read and analyze project-specific documentation and scripts, which serves as a data ingestion surface for potential indirect instructions.
- Ingestion points: Project workflow documentation, test scripts, fixtures, and CI configurations (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the analyzed data.
- Capability inventory: The skill is designed to read files and execute local project commands to verify environment readiness and behavior.
- Sanitization: No explicit sanitization or validation of the content from the analyzed files is specified.
- [SAFE]: The skill incorporates a security best practice by directing the agent to use references for credentials rather than copying sensitive values into the output documentation.
- [SAFE]: The skill references an external methodology from a well-known technology organization's repository (Cursor) for instructional purposes without executing remote code.
Audit Metadata