discord

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: All identified actions and instructions are consistent with the skill's purpose. The use of the 'message' tool is restricted and correctly configured.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external Discord messages. Evidence: (1) Ingestion points: 'read' and 'search' actions in SKILL.md; (2) Boundary markers: No explicit markers defined; (3) Capability inventory: Includes sending, editing, deleting, and reacting to messages; (4) Sanitization: No sanitization logic is specified. While this surface exists, it is inherent to the skill's primary function of chat management and is considered acceptable under standard operating conditions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 01:08 AM
Security Audit — agent-trust-hub — discord