drafting-messages
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill contains only natural language instructions to guide the agent's tone and formatting when drafting replies for users.
- [NO_CODE]: No scripts, binary files, or command-line operations are present in the skill definition.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (such as chat history or PR comments) as part of its primary function, but it lacks any tools or system capabilities that could be exploited. 1. Ingestion points: User-provided text and external message context. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined. 3. Capability inventory: No tool access, network capabilities, or file system operations are requested or used. 4. Sanitization: None.
Audit Metadata