check-tests
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is configured to read content from the
tests/**directory. This creates a surface where instructions embedded in test files could potentially influence the agent's behavior during the check. - Ingestion points: File system access to
tests/**as specified inrouting.json. - Boundary markers: No explicit markers or delimiters are defined in the instructions to separate untrusted test data from agent instructions.
- Capability inventory: The skill contains no scripts or subprocess calls; it relies on the agent's native file reading capabilities.
- Sanitization: No sanitization or validation of the test file content is mentioned.
- [NO_CODE]: The provided files consist entirely of markdown instructions and a routing configuration file. No executable scripts (Python, Shell, JavaScript) are included in the skill.
Audit Metadata