golden-html-multi
Warn
Audited by Snyk on Jun 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). Outsider-free text is ingested because the skill’s runtime workflow is an “HTML Scraper” that processes external HTML files (e.g.,
intro.html/extras.html) into readable markdown (references/golden_html_multi_s1-s2.md,...s3-s4.md) which is then fed into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata