ticket-tracker
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub issues which could be used to influence the agent's behavior.
- Ingestion points: The skill executes
gh issue list(SKILL.md) to retrieve titles and labels which are then processed by the LLM. - Boundary markers: There are no boundary markers or instructions to ignore embedded commands within the issue data.
- Capability inventory: The skill possesses the capability to modify repository state via
gh issue edit,gh issue close, andgh issue reopen(SKILL.md). - Sanitization: No sanitization or validation of the external issue data is performed before it is used in the agent's context.
- [PROMPT_INJECTION]: The skill contains instructions that direct the agent to withhold specific information from the user, which can be a technique used to hide state changes or influence user perception.
- Evidence: Instructions such as "Do not tell the user the roadmap is superseded" and "omit unless asked" (SKILL.md) represent a form of information concealment, although likely intended for UI/UX optimization.
Audit Metadata