weekly-planning
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting untrusted data from external sources.
- Ingestion points: External issues and project items are retrieved via
gh search issues(SKILL.md). - Boundary markers: The skill does not implement delimiters or 'ignore' instructions for external content.
- Capability inventory: The agent can create issues across repositories and modify project boards using
gh project item-add(SKILL.md). - Sanitization: There is no evidence of filtering or sanitizing issue titles or bodies before they are processed by the agent.
Audit Metadata