llm-communication
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): The skill consists exclusively of markdown documentation providing guidance on prompt engineering best practices.
- [NO_CODE] (SAFE): No scripts, binaries, or executable components are included. The command snippets provided in the text are purely illustrative examples of what not to do when writing instructions.
- [PROMPT_INJECTION] (SAFE): The skill discusses prompt structures and mentions common keywords like 'IMPORTANT' and 'CRITICAL', but only as examples of poor instruction writing. It does not contain any attempts to bypass safety filters or override agent behavior.
- [DATA_EXFILTRATION] (SAFE): No network operations or file system access patterns were detected.
Audit Metadata