test-case-writer
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and does not include any scripts, commands, or binary files.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external requirements (untrusted data). However, it lacks any functional capabilities (such as shell execution, file writes, or network requests) to act on malicious instructions embedded in that data. Evidence chain:
- Ingestion points: Processes user requirements and stories provided in the input context.
- Boundary markers: None present to delimit external instructions.
- Capability inventory: No dangerous tools or commands are requested or used.
- Sanitization: No sanitization is performed on input text.
Audit Metadata