interview
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze data from external, potentially untrusted sources such as repository code, tests, and issue records.
- Ingestion points: The instructions specify reading the caller's input, repository code, tests, and linked records in SKILL.md (Section 1, Step 1).
- Boundary markers: There are no instructions defining the use of delimiters or 'ignore' instructions to prevent the agent from obeying commands embedded in the analyzed data.
- Capability inventory: The skill primarily involves reading and reasoning; it does not explicitly invoke shell commands, network operations, or file-writing tools within its own instructions.
- Sanitization: The skill lacks steps for sanitizing or filtering external content before it is processed by the agent.
Audit Metadata