web-security
Warn
Audited by Snyk on Nov 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The black-box workflow fetches pages and bundles from a user-supplied live site and reads plugin
readme.txtfiles, which are arbitrary outsider-authored content the agent must actively select and fetch, so this is low rather than medium.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill documents operational changes it can perform, such as deploying Turnstile and secrets, setting
workers_dev = false, editing.npmrc, changing DNS and WAF rules, and rotating credentials, but it establishes no explicit irreversible loss of operational state, so the scope stays at low.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata