web-auth
Warn
Audited by Snyk on Mar 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: 0.80). The SKILL.md shows the agent opens real web pages (provider logins like twitter/github and arbitrary --url values) and parses page content/success-selectors/headlessVerification to determine auth success, so untrusted third-party page content can influence the agent's decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata