discord-skill

Warn

Audited by Snyk on Feb 27, 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). The skill directly fetches and reads user-generated content from Discord (see discord_skill.py commands like cmd_messages -> GET /channels/{channel_id}/messages and cmd_search -> GET /guilds/{guild_id}/messages/search, and the SKILL.md "Read messages from channel" / "Search messages") so untrusted third‑party messages can be ingested and could influence the agent's subsequent decisions or tool use.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 03:20 PM