om-auto-merge-triage

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 runs list-prs on the tracker's open PRs and reads their titles, bodies, comments, and review comments during AI judgment, and anyone who can post on a PR can supply that text without the agent selecting it first.

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 can apply the automerge label to PRs after human confirmation, which enables unattended merge automation, but the label is reversible and no irreversible operational loss is established, so gate 2 fails.

Issues (2)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 21, 2026, 04:53 PM
Issues
2