nopus-simplify
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill operates entirely within the conversation context to provide stylistic rewrites. It does not request tool access, perform external downloads, or interact with the operating system.
- [PROMPT_INJECTION]: No attempts to override system instructions, bypass safety filters, or extract system prompts were found. The instructions focus strictly on formatting and clarity.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests text from the conversation history (the preceding assistant response). 1. Ingestion point: Previous assistant response in SKILL.md. 2. Boundary markers: None present. 3. Capability inventory: No tools or model invocation permitted via frontmatter configuration. 4. Sanitization: None present. While this ingestion surface exists, the restricted capability tier renders the implementation safe.
Audit Metadata