context-recovery
Warn
Audited by Snyk on Mar 24, 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's mandatory Recovery Workflow (Step 2: "Read Channel History" with message:read for Discord/Slack/Telegram/Signal in SKILL.md) ingests and parses user-generated messages from third-party channels and then synthesizes that content to drive follow-up actions, so untrusted external content can influence agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata