cold-email

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill contains instructions to use sensitive signals to inform outreach without disclosing them to the recipient. This is a sales strategy for relevance and not a malicious attempt to hide information from the user.
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches data from external websites, creating an attack surface for indirect injection. However, it includes explicit instructions to treat fetched content as data rather than instructions, mitigating the risk.
  • [SAFE]: The skill's file operations are limited to reading and writing a local context file in the .agents/ directory, which is transparent and relevant to its function.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 04:07 PM