coordinator
Warn
Audited by Snyk on Nov 21, 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). The required workflow reads GitHub PR state and diffs, and T3 wakes the coordinator on a watched PR's comments and reviews (SKILL.md step 4 PR watch), so outsiders who can comment on a public PR can push free text into a feed the workflow consumes without the agent selecting it.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill installs a persistent OS timer (launchd or systemd) that runs
tick.shevery 10 minutes, which is an operational change, but no supplied text establishes an irreversible loss of operational state, and PR merges are content changes that the skill gates on user approval and describes as undoable.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata