qa-spec-writer
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes requirement documents provided by manual input or other skills, which constitutes a surface for indirect prompt injection if the input contains malicious instructions.
- Ingestion points: The skill reads requirements documents in the first step of its workflow (SKILL.md).
- Boundary markers: Absent. The skill instructions do not specify the use of delimiters or instructions to the agent to treat requirement content as untrusted data.
- Capability inventory: The skill has the capability to write files to the 'docs/specs' directory and invoke the 'qa-diagram-generator' skill.
- Sanitization: There is no evidence of sanitization, validation, or escaping of the input requirement text before it is processed by the agent.
Audit Metadata