chrome-devtools

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's examples and workflows explicitly pass sensitive values (e.g., passwords) as literal CLI arguments like --value "secret", which instructs the agent to generate commands containing secrets verbatim, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md repeatedly instructs running Puppeteer scripts (e.g., navigate.js, evaluate.js, snapshot.js, screenshot.js) with arbitrary --url values to navigate, scrape, execute JS, extract elements and follow-up (click/fill) on public websites (e.g., "node navigate.js --url https://example.com" and the "Web Scraping" and "Chain Commands" workflows), so the agent will fetch and interpret untrusted third-party web content which can influence subsequent tool actions.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill instructs running installation scripts and explicit sudo apt-get commands (e.g., ImageMagick and system libraries via install-deps.sh), which modify system state and require elevated privileges, so it risks compromising the host.