content-writer
Warn
Audited by Snyk on Jul 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The skill’s refresh mode ingests candidate URLs/content and competitor examples (outsider-authored page text) from user-provided URLs/content, which can become readable prose in the agent’s LLM context via the “Reads” path for refresh-mode inputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata