behavioral-modes
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of markdown instructions defining operational modes for an AI agent. No executable code or suspicious behaviors were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing user-supplied keywords to trigger different behavioral modes. Given the restricted tool access defined in the frontmatter, this does not pose a significant risk.
- Ingestion points: User prompts containing triggers for mode detection (SKILL.md).
- Boundary markers: None explicitly defined.
- Capability inventory: The skill is limited to Read, Glob, and Grep tools as configured in the SKILL.md frontmatter.
- Sanitization: No sanitization steps are described for user-supplied triggers.
Audit Metadata