PromptInjection
Warn
Audited by Snyk on Jun 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill’s required runtime workflow performs browser-based reconnaissance and network capture against a user-supplied target URL (e.g.,
browser navigate https://target-app.comandbrowser extract ...inWorkflows/Reconnaissance.md), which can ingest outsider-authored free text from the fetched web page/DOM into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata