draft-outreach

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a transparent and benign workflow for professional outreach, using web research and user-authorized connectors to personalize messages.
  • [SAFE]: No evidence of prompt injection, obfuscation, or suspicious command execution was found. The skill operates within the scope of its described productivity purpose.
  • [SAFE]: Although the skill processes untrusted web content (creating an indirect prompt injection surface), the risk is minimal as the output is restricted to outreach drafts. Ingestion points: Web search results via research-prospect skill. Boundary markers: Absent. Capability inventory: Text generation and draft creation via authorized connectors. Sanitization: None identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 03:21 PM
Security Audit — agent-trust-hub — draft-outreach