paw-mkt-cro

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

• Third-party content exposure detected (low risk: 0.10). The agent skill instructs the LLM to perform live website URL audits and competitor benchmarking using agent-browser or WebFetch to ingest public web pages, which are classified as low risk for indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill references an external GitHub repository (https://github.com/vercel-labs/agent-browser) in setup instructions and workflow documentation, which is fetched and installed at runtime via npx skills add or npm install under weak/unknown or reputable unofficial provenance, meeting the threshold for an operational dependency.