epic-requirement-reviewer
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and analyze content from external, potentially attacker-controlled sources such as issue tracker comments, subissue descriptions, and linked documentation.
- Ingestion points: The skill reads full requirements, subissue descriptions, parent discussions, and linked documents (SKILL.md, Workflow Step 1).
- Boundary markers: There are no instructions to the agent to treat the external data as untrusted or to use delimiters to separate instructions from data.
- Capability inventory: The skill utilizes authorized tracker tools to fetch content and accepts local directories or pasted text for review.
- Sanitization: The instructions do not define any sanitization, filtering, or validation steps for the content retrieved from external sources before it is processed by the agent.
Audit Metadata