extract-pdf
Warn
Audited by Snyk on Aug 26, 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). At runtime, the skill’s cascade workflow reads text extracted from the user-supplied PDF file (e.g., block.get("text") passed into the header-verdict classifier runner), meaning outsider-authored content in the PDF can influence LLM/escalation-relevant decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata