om-auto-implement-spec
Warn
Audited by Snyk on Aug 12, 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). Step 1/2 of the required workflow reads outsider-authored text from the tracker by using tracker operations like get-issue and get-pr (and it can search-resume PRs via search-prs), meaning the agent can ingest issue/PR bodies/comments authored by repository users at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata