cold-email-craft
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources (e.g., recipient roles, public company signals, LinkedIn content) to populate email templates. This creates a surface for indirect prompt injection if those external sources contain adversarial instructions designed to influence the agent's behavior during the drafting process.
Audit Metadata