test-case-authoring
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data in the form of work items, tickets, and acceptance criteria provided by users. A malicious actor could embed instructions within these items to manipulate the agent's output or behavior.
- Ingestion points: The workflow in SKILL.md (Step 1) requires reading user-provided items, including titles, acceptance criteria, and repro steps.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' blocks to separate untrusted content from the system instructions.
- Capability inventory: The skill specifies file-writing capabilities, instructing the agent to save output as 'test-plan-[ticket-id].md' as specified in the Output format section.
- Sanitization: There are no requirements to sanitize or escape the content of the ticket before it is incorporated into the generated test plan or traceability matrix.
Audit Metadata