cold-email
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns detected. The skill consists of instructional text for email writing and research. The instructions involves reading local marketing files for context, which is a legitimate use of project data within the agent's environment.
- [PROMPT_INJECTION]: The skill exhibits surface area for indirect prompt injection by processing external prospect data and local context files.
- Ingestion points: Local marketing context files (e.g., .agents/product-marketing.md) and user-provided research signals such as LinkedIn posts or company news.
- Boundary markers: Absent.
- Capability inventory: Email text generation. No code execution, subprocess calls, file writing, or network operations are present.
- Sanitization: Absent. The risk level is considered low because the skill's capabilities are restricted to providing text output.
Audit Metadata