p7
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security threats were identified. The skill contains only instructional markdown for an agent persona. No executable scripts, network requests, or sensitive file accesses are present. Protocol references such as
../pua/references/p7-protocol.mdtarget local context. - [INDIRECT_PROMPT_INJECTION]: The skill is triggered by user input but lacks exploitable actions. 1. Ingestion points: User triggers 'P7模式' and '方案驱动' in SKILL.md. 2. Boundary markers: None. 3. Capability inventory: Text generation only; no command execution or network access. 4. Sanitization: None.
Audit Metadata