safha
Warn
Audited by Snyk on Jul 7, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). SKILL.md describes a runtime workflow that scrapes arbitrary public web pages/URLs (outsider-authored content) and ingests their article text into the tool’s output (e.g., the “text” field), which would then be available for any downstream LLM context usage.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata