grade-tests
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill analyzes external code provided as test methods or file spans. This represents a potential surface where instructions embedded in code comments or strings could attempt to influence the agent's behavior. * Ingestion points: Test bodies and production code are read from user-specified files or provided directly as input. * Boundary markers: The skill does not explicitly specify the use of delimiters when processing the source code content. * Capability inventory: Actions are limited to reading local files and calling internal analysis skills; there are no network or file-write operations. * Sanitization: No specific sanitization or escaping of the input source code is defined beyond identifying the method boundaries.
Audit Metadata