web-search-plus
Warn
Audited by Snyk on Apr 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill clearly fetches and ingests untrusted public web content (e.g., Perplexity via Kilo that "reads pages and summarizes" and returns synthesized answers, You.com's "livecrawl" full-page content, and Tavily's "raw_content") as documented in SKILL.md/README.md and implemented in scripts/search.py, and that third‑party content is parsed and used to produce answers and guide routing/decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata