characterization-test-writer
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions for a standard software engineering task. It suggests using well-known, reputable libraries such as freezegun and ApprovalTests. No malicious patterns, obfuscation, or unauthorized access attempts were found.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external code and production data to generate test cases. 1. Ingestion points: The skill instructions refer to gathering legacy code, dependency lists, and production logs/inputs in SKILL.md. 2. Boundary markers: No specific delimiters or instruction-bypass warnings are defined for the inputs. 3. Capability inventory: The skill generates code assertions based on observed outputs; it relies on the execution of the target code within a testing environment. 4. Sanitization: There are no specific instructions for filtering or sanitizing production data or logs before they are used to generate tests.
Audit Metadata