competitor-mention-handling
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional, providing guidelines and best practices for sales bots when handling competitor mentions. It does not contain any executable code, scripts, or network requests.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external inputs (prospect messages containing competitor names), which is a potential injection surface. However, the skill lacks any capabilities—such as file writing, network access, or command execution—making this surface benign in this context.
- Ingestion points: Prospect dialogue examples in SKILL.md.
- Boundary markers: None specified.
- Capability inventory: None. No tools or scripts are present.
- Sanitization: None specified.
Audit Metadata