ticket-to-pr
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (ticket descriptions) to drive automated repository actions across multiple steps.
- Ingestion points: Ticket content is passed to the skill as command arguments in the harness (SKILL.md).
- Boundary markers: The skill lacks explicit boundary delimiters or instructions to the model to ignore potential instructions embedded within the ticket body itself.
- Capability inventory: The skill possesses the capability to modify local and remote git state via
git(branch, commit, push) and create networked entities via the GitHub CLI (gh). - Sanitization: No sanitization or validation of the ticket content is performed before the harness/LLM uses those details to implement code changes.
Audit Metadata