grade-tests
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external data in the form of test method bodies, production source code, and diff hunks provided via user-specified file paths or PR identifiers. This creates an attack surface where instructions embedded in the analyzed code could attempt to influence the agent.
- Ingestion points: Step 2 involves reading method bodies and production code from the filesystem based on user input.
- Boundary markers: The instructions do not specify the use of delimiters or specific system instructions to disregard potentially malicious content within the analyzed source code.
- Capability inventory: The skill is scoped to reading files and invoking a local extension skill (
test-analysis-extensions); it does not contain instructions for network exfiltration, file writing, or arbitrary command execution. - Sanitization: There is no evidence of input validation or escaping for the source code strings before they are interpolated into the prompt context.
Audit Metadata