herdr-agent-coordination
Warn
Audited by Snyk on Aug 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In SKILL.md the receiving workflow “Inspect the origin” by running
herdr --session <session> agent read <origin-pane> --source <visible|recent-unwrapped>which ingests other peers’ free-text/transcripts as the origin-pane contents regardless of whether the sender was trusted.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata