paw-mkt-paid-ads

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

• Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to perform competitive ad research by reading text content extracted from external ad libraries and competitor landing pages using browser automation and web fetch tools.

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

• Potentially malicious external URL detected (high risk: 0.70). An operational dependency on an external tool installation via npm/npx (https://github.com/vercel-labs/agent-browser) is evidenced in shared patterns and competitive research, but its provenance is weak/unknown/suspicious because it points to an arbitrary third-party GitHub repository without immutable verification or official vendor binding.