agent-council

Warn

Audited by Snyk on Feb 14, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). This skill binds agents to Discord channels (see scripts/create-agent.sh, scripts/setup_channel.py, and the gateway "bindings"/"channels" entries in SKILL.md/README) and the documentation explicitly describes agents "seeing" and responding to channel messages, so the agent will read and act on user-generated, untrusted Discord content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 14, 2026, 07:50 PM