product-management-patterns
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow that involves ingesting user feedback and needs to perform prioritization and task management on GitHub. This creates an attack surface where malicious instructions embedded in user content could influence the agent's behavior when planning roadmaps or assigning issues.
- Ingestion points: User feedback, market research, and user needs documentation (SKILL.md).
- Boundary markers: None identified in the provided instructions to delimit external data from agent instructions.
- Capability inventory: The skill specifies interaction with GitHub issues, including writing descriptions, labeling, and assigning tasks (SKILL.md).
- Sanitization: No sanitization or validation mechanisms are defined for the ingested feedback.
Audit Metadata