todd-brown-emf
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill consists entirely of instructional text and prompt templates for marketing copy generation.
- [PROMPT_INJECTION]: Prompt templates use standard persona adoption (e.g., 'Act as a direct response strategist') for legitimate task fulfillment without attempting to bypass safety filters or override system instructions.
- [DATA_EXFILTRATION]: No network operations, sensitive file path access, or credential harvesting patterns were identified.
- [REMOTE_CODE_EXECUTION]: No external dependencies, package installations, or remote script execution patterns are present in the skill.
- [INDIRECT_PROMPT_INJECTION]: While the skill ingests user data for marketing fields, it possesses no technical capabilities (file system access, shell execution, or network requests) that could be exploited via injection.
Audit Metadata