clean-code

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's Verification Scripts explicitly include commands that take arbitrary URLs (e.g., performance-optimizer: lighthouse_audit.py <url> and test-engineer: playwright_runner.py <url>), which require fetching and analyzing open/public web pages and then having the agent read and summarize the script output, exposing it to untrusted third-party content.