bro
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill is designed for text summarization and simplification. It does not utilize any tools, perform network requests, or access the file system.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external text from previous assistant messages as its primary input.
- Ingestion points: The instructions specify rewriting the "previous assistant message" (SKILL.md).
- Boundary markers: No explicit boundary markers or instruction-isolation delimiters are defined.
- Capability inventory: The skill configuration explicitly sets
disable-model-invocation: true, preventing the agent from calling any tools or performing system actions regardless of input content. - Sanitization: No specific sanitization or filtering logic is implemented for the input text.
Audit Metadata