aeo-optimizer

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime path can ingest “Article content” from an outsider-authored URL: if the user provides a URL, Claude fetches the page and extracts the main article body, which is outsider free text that becomes LLM-readable context (public web content fetched at runtime).

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly fetches a user-provided URL at runtime ("If providing a URL instead of pasted text, Claude will fetch the page") — any external http(s) page supplied by the user (e.g. the provided article URL) would be ingested and therefore can directly control the agent's prompts and output.