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.txt files, 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
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 21, 2026, 01:03 AM
Issues
2