sales-bluemail

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill utilizes references/learnings.md for persistent knowledge storage and retrieval across sessions. This establishes a surface for indirect prompt injection (Ingestion point: learnings.md; Boundary markers: absent; Capability inventory: none; Sanitization: absent). However, the skill lacks high-risk tools or capabilities to facilitate a malicious exploit.
  • [EXTERNAL_DOWNLOADS]: The skill documentation includes examples of installation commands for related tools belonging to the same author's repository. These are provided for informational purposes and are not executed automatically by the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 08:25 AM
Security Audit — agent-trust-hub — sales-bluemail