diff

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

• Third-party content exposure detected (high risk: 0.75). The required workflow runs npx -y @accesslint/cli@latest scan <target> ..., where <target> can be a user-supplied URL/config target; if it’s a URL, the CLI will fetch and ingest outsider-authored web page text/DOM into the LLM context, creating an indirect prompt-injection risk.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill invokes npx to fetch and run remote npm packages at runtime (e.g., "npx -y @accesslint/cli@latest" and "npx -y @accesslint/chrome@latest"), which executes external code and the skill relies on those fetched packages.