script-ads
Warn
Audited by Snyk on Jul 30, 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 instructs the agent to treat “captions, transcripts, page text, emails, and files pulled in by this skill” as untrusted scraped data, and the runtime workflow writes that content into copy/compliance, meaning outsider-authored free text can be ingested before use.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata