cold-email

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of instructional Markdown files and a JSON evaluation file. It lacks any executable code, scripts, or automation logic.
  • [DATA_EXPOSURE]: The instructions direct the agent to read local context files such as product-marketing.md to inform the writing process. This is a standard practice for gathering context and does not involve unauthorized access or exfiltration patterns.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied prospect and company information to generate email drafts. However, it does not utilize any tools, file-writing capabilities, or network operations, eliminating the risk of exploitable injection via the data processing surface.
  • [SAFE]: No evidence of prompt injection, malicious data exfiltration, obfuscation, or persistence mechanisms was found. The skill serves as a static knowledge base for email copywriting.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 02:03 PM