weekly-report
Warn
Audited by Snyk on Aug 18, 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). [SKILL.md] describes building “dossiers” by reading the full diff of commits in a specified branch window (and optional Azure Boards records), so outsider-authored text can enter the workflow via commit messages/diffs and be ingested directly into the per-issue diff-reading subagents.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata