wait-what
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no executable code, network operations, or sensitive data access. It serves as a stylistic template for the AI agent.
- [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill instructs the agent to read
CONTEXT.mdandCONTEXT-MAP.mdfrom the local repository (referenced in SKILL.md). - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat these files as untrusted content.
- Capability inventory: No capabilities (tools, shell, network, file-write) are requested or available in this skill.
- Sanitization: No sanitization is performed on the ingested content, though the lack of capabilities prevents exploitation.
Audit Metadata