mstack
Warn
Audited by Snyk on Nov 20, 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 Recall and Why workflows read outsider-authored text from monitored feeds, including GitHub PR comments and reviews (
gh pr view ... comments,reviews), issue trackers, team chat, and error trackers, without the agent first selecting a specific item.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). Branch and worktree cleanup via
wtand symlink installation into a skill root are state-changing local operations, but the gate fails for irreversible loss because no supplied text shows unrecoverable loss of operational state.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata