wk-self-perf
Warn
Audited by Snyk on Aug 19, 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 Stage 1, the workflow uses agent tools to fetch outsider-authored free text from GitHub (PRs/issues), Slack messages, Gmail emails, and Jira/Confluence content, and then reads and synthesizes those reference files in Stage 2.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata