iblai-marketing-copy-editing
Warn
Audited by Snyk on Aug 2, 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 skill’s runtime path reads and edits user/provided marketing copy directly via the evaluation prompts, which are outsider-authored free text (“Edit this homepage copy…”, “Quick edit on this CTA section…”, etc.) and then applies the Seven Sweeps on that same text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata