aeo-visibility

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches data from external sources to perform its primary function. It makes network requests to official AI service APIs (OpenAI, Google Gemini, Perplexity, and Tavily) and retrieves content from arbitrary URLs provided for SEO auditing. These operations target well-known and trusted service providers.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted data from external websites and AI engine outputs which the agent then evaluates and scores.
  • Ingestion points: External website content fetched via fetch_page.py and response text from AI engines via query_engines.py are written to the workspace and subsequently processed by the agent.
  • Boundary markers: None identified; untrusted content from the JSON artifacts is passed to the agent for analysis without explicit delimiters or instructions to ignore embedded commands.
  • Capability inventory: The skill executes local Python scripts to perform network communication and file system operations within the workspace.
  • Sanitization: No content sanitization or validation is performed on the external data before it is presented to the agent for scoring.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 04:03 PM
Security Audit — agent-trust-hub — aeo-visibility