cold-email
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of text-based instructions and reference guides for email copywriting. No executable scripts, subprocess calls, or remote code patterns were identified.
- [SAFE]: File access is limited to local project context files (e.g., .agents/product-marketing.md) for gathering marketing information, which is consistent with the skill's purpose and does not involve sensitive system or credential files.
- [SAFE]: No evidence of prompt injection or obfuscation was found in the instructions or metadata.
- [SAFE]: While the skill processes prospect-specific data (e.g., LinkedIn posts) which could harbor indirect prompt injections, the lack of tool-based capabilities or executable scripts makes this surface a negligible risk. * Ingestion points: Prospect research signals and data requested in SKILL.md. * Boundary markers: None specified in the instructions. * Capability inventory: None (the skill is limited to text generation). * Sanitization: None provided.
Audit Metadata