web-ai
Warn
Audited by Snyk on May 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill drives and reads responses from third-party AI provider web pages (e.g., the SKILL.md examples and workflow for agbrowse web-ai query that navigate to provider URLs like https://chatgpt.com/ and https://gemini.google.com/app and poll/consume the provider's page responses), so untrusted external content could be interpreted and influence subsequent tool actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata