triage
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing external, untrusted data.
- Ingestion points: The skill explicitly instructs the agent to read issue or pull request titles, bodies, and comments from a tracker (documented in
SKILL.mdunder 'Workflow -> 1. Gather the full tracker context'). - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing this external content.
- Capability inventory: The skill requires codebase access, documentation access, and the ability to interact with the issue tracker (commenting and labeling), providing a path for injected instructions to influence repository state.
- Sanitization: There is no mention of sanitizing, escaping, or validating the external data before it is incorporated into the agent's context.
Audit Metadata