wait-what
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill contains no executable code, shell commands, or network operations. It consists entirely of instructions to modify the agent's linguistic style using project-specific documentation.
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to ingest content from
CONTEXT.mdandCONTEXT-MAP.mdto inform its responses. While this creates a data ingestion surface, the risk is negligible as the skill has no capabilities to execute commands or exfiltrate data. - Ingestion points: Reads local
CONTEXT.mdandCONTEXT-MAP.mdfiles (referenced inSKILL.md). - Boundary markers: None specified.
- Capability inventory: No tools, code execution, or network operations are present in the skill configuration.
- Sanitization: None present.
Audit Metadata