knowledge-update
Warn
Audited by Snyk on Jul 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). SKILL.md’s required workflow reads outsider-authored free text from the bound wiki and/or an externally provided
--source(URL/file) at runtime (“Read the current page and the source”: read full page text and, fornew-source, read the new source fully), which then gets surfaced in plain-prose diff context for the LLM to use.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata