scan

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow runs npx -y @accesslint/cli@latest scan <target>, where <target> can be a user-supplied URL; the LLM context risk comes from the CLI ingesting and then emitting scraped page text/DOM-derived strings (outsider-authored web content) as part of the JSON report that the agent would read.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill runs npx to fetch and execute remote npm packages at runtime (e.g., "npx -y @accesslint/chrome@latest" and "npx -y @accesslint/cli@latest"), which downloads and runs external code the skill relies on.