Email Composer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [No Code] (SAFE): The skill provides only markdown-based instructions and examples for text generation. No scripts (.sh, .py, .js) or configurations that trigger command execution were found within the provided file.
- [Indirect Prompt Injection] (LOW): Workflows like 'Reply to Email Thread' involve ingesting untrusted external data. While this presents an ingestion surface, the skill lacks any associated capabilities (such as file-writing or network tools) that could be abused if malicious instructions were embedded in the processed threads.
Audit Metadata