goose-ads

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches competitor ad intelligence and scraper recipes from external sources, which can contain outsider-authored free text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to fetch external analytics recipes and tools on demand from goose-skills and run shell/CLI commands using the gooseworks utility, representing an unverified remote runtime operational dependency.