web-search
Warn
Audited by Snyk on Jun 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.92). The skill’s runtime path fetches and extracts outsider-authored web page text/snippets from public search results (e.g.,
server/search/bing.ts/server/search/google.tsviapage.goto(...)andpage.evaluate(...)), which then gets returned as Markdown and fed into the agent’s LLM context.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). High-confidence: the startup script (scripts/start-server.sh) can run npm install at runtime (install_dependencies), which fetches and installs code from the npm registry (e.g. https://registry.npmjs.org/) that will be executed by the Bridge Server — a required runtime dependency that can introduce remote code execution risk.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata