aeo-run

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md and README explicitly run goose-aeo which queries external AI search engines (ChatGPT, Perplexity, Gemini, Grok, Claude, DeepSeek) and analyzes those third-party responses for brand mentions, so the agent consumes and acts on untrusted public content from those sources.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill invokes "npx goose-aeo" at runtime and lists/links the upstream repository https://github.com/athina-ai/goose-aeo, which means it will fetch and execute remote package code (from the npm registry / that repo) as a required runtime dependency.