audit-ux

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

• Third-party content exposure detected (low risk: 0.10). SKILL.md requires the agent to use Firecrawl to scrape official third-party pages (e.g., https://lawsofux.com) and search/scrape NN/g and Intuit microcopy sites before auditing, which ingests outsider-authored free text from those pages at runtime.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill issues a runtime scrape (firecrawl:firecrawl_scrape) of https://lawsofux.com and instructs using the scraped content to drive the evaluation, meaning remote content is fetched at runtime and injected into the agent's prompt/context.