epic-hypothesis
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied epic ideas and initiatives, creating a surface for indirect prompt injection. The risk is negligible as the skill is purely instructional and lacks access to dangerous tools (network, shell, file-write). * Ingestion points: User-provided text describing initiatives or epic ideas via arguments or pasted context (SKILL.md). * Boundary markers: None present. * Capability inventory: Purely instructional text generation; no tool use or dangerous capabilities identified. * Sanitization: None present.
- [SAFE]: The skill references a GitHub repository (github.com/deanpeters/product-manager-prompts) belonging to the author, which represents a legitimate vendor resource.
Audit Metadata