task-to-pr
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data from ticket IDs, URLs, descriptions, and comments. This creates a risk of indirect prompt injection where malicious instructions embedded in a ticket could influence the agent's subsequent actions, such as writing malicious code or performing unauthorized git operations.
- Ingestion points: The agent reads ticket content, user comments, and linked context like design docs or specifications (SKILL.md).
- Boundary markers: The instructions do not specify any delimiters or warnings to ignore embedded instructions within the ingested ticket data.
- Capability inventory: The agent has the ability to implement code changes, branch, commit, push, and open pull requests (SKILL.md).
- Sanitization: There is no mention of sanitizing or validating the ticket content before it is used to guide the implementation and review process.
Audit Metadata