blog
Warn
Audited by Snyk on Aug 27, 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
scripts/blog.shskill constructsDIFF_OUTPUTfrom the current user repo’s branch/staged diff (git diff ...) and then embeds that diff-derived data intoBODY_MD//tmp/blog-input.jsonbefore callingcreateBlogPost(), so outsider-authored free text (code/diffs committed by a non-trusted contributor) is ingested at runtime without selecting a specific item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata