cold-email
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill is composed of Markdown documentation and reference data. It contains no executable scripts, system commands, or binary files.
- [SAFE]: No remote code execution or unauthorized external downloads were found. External references point to legitimate documentation and third-party marketing tools.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting external data, creating a potential surface for indirect injection.
- Ingestion points: LinkedIn posts, company news, and local context files like product-marketing.md are used for personalization.
- Boundary markers: The instructions lack explicit delimiters to separate external content from system prompts.
- Capability inventory: The skill's actions are restricted to drafting text; it has no access to command execution or sensitive file operations.
- Sanitization: No sanitization steps are provided for external research signals.
Audit Metadata