cold-email
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely instructional, providing the agent with expert knowledge on B2B cold email strategies, deliverability infrastructure, and follow-up cadences. No malicious patterns or executable scripts were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read a local configuration file
.agents/sales-context.mdfor project-specific sales information. While this incorporates external data, the risk is negligible as the agent's output is limited to generated email text and it lacks tool-based capabilities for exfiltration. * Ingestion points: Reads.agents/sales-context.md. * Boundary markers: None. * Capability inventory: No tools or execution methods are used. * Sanitization: None.
Audit Metadata