google-maps-api-skill

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md and scripts/google_maps_api.py explicitly call the BrowserAct Google Maps workflow (https://api.browseract.com/...) to fetch business listings, reviews, websites, and other Google Maps content (user-generated/open-web data), which the agent reads and acts on as part of its workflow — exposing it to untrusted third-party content that could carry indirect prompt-injection payloads.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's script calls the BrowserAct API at runtime (https://api.browseract.com/v2/workflow), using a workflow_template_id to start and poll tasks on BrowserAct's platform — which causes remote execution of workflows the agent depends on, so the external URL directly executes remote code required for the skill.