to-tickets
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources and local files to generate its output, creating a surface for embedded instructions to influence agent behavior.
- Ingestion points: The process fetches context from user-provided spec paths, issue numbers, or URLs (SKILL.md, Step 1).
- Boundary markers: The instructions lack specific delimiters or "ignore" directives to isolate external content from the agent's core instructions.
- Capability inventory: The skill possesses the ability to read local files, write to the local filesystem (under .scratch/), and perform network operations to publish issues to trackers like GitHub or Linear (SKILL.md, Step 5).
- Sanitization: While no automated sanitization is described, the skill enforces a manual human-in-the-loop validation step ("Quiz the user") to review all drafted tickets before they are published (SKILL.md, Step 4).
Audit Metadata