acceptance-criteria-writing
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional, defining a process for an agent to generate acceptance criteria. It does not contain executable code, remote script downloads, or requests for sensitive system access.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided story requirements which constitutes an attack surface. However, the risk is mitigated as the skill's primary function is restricted to producing structured text and diagrams for review. There are no high-privilege capabilities exposed that could be abused via malicious data injection.
- Ingestion points: Story/feature description provided by the user in Phase 1.
- Boundary markers: The output is encapsulated in a structured report template.
- Capability inventory: File writing (mentions saving the report) and diagram rendering via a referenced mixin.
- Sanitization: Standard LLM guardrails apply; no explicit sanitization logic is defined in the instructions.
Audit Metadata