seo-dataforseo

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill provides an entry point for indirect prompt injection by ingesting vast amounts of untrusted data from across the web.
  • Ingestion points: The agent retrieves untrusted content from Google search results, YouTube video comments via serp_youtube_video_comments_live_advanced, and full web pages via on_page_content_parsing and ai_optimization_chat_gpt_scraper.
  • Boundary markers: There are no explicit instructions for the agent to use data delimiters or to ignore potential instructions embedded within the fetched SEO data.
  • Capability inventory: The skill environment is configured with Bash and Write tools, which could be abused if the agent is tricked by malicious prompts in the ingested data.
  • Sanitization: The instructions do not define any sanitization, filtering, or validation steps for content retrieved from external sources.
  • [COMMAND_EXECUTION]: The skill documentation requires the execution of a local shell script (./extensions/dataforseo/install.sh) to install prerequisites, which involves running commands in the local execution environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 08:40 AM
Security Audit — agent-trust-hub — seo-dataforseo