ticket-requirements-gathering
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, potentially untrusted sources such as issue trackers, repository code, and pull requests.
- Ingestion points: Documented in the 'Setup' phase (steps 2, 3, and 4), where the agent reads tickets, parent epics, repository instructions, and draft work.
- Boundary markers: The instructions do not explicitly mandate delimiters for external content, but they enforce a strict procedural framework where the agent must 'Interview the user one question at a time'.
- Capability inventory: The skill does not perform direct code execution or network operations itself. Its primary outputs are documentation artifacts (specs and plans).
- Sanitization: There is no explicit sanitization step for ticket content; however, the skill requires explicit human approval for both the 'Spec/design' and the 'Implementation plan', which serves as a robust security control against malicious instructions embedded in tickets.
Audit Metadata