seo-dataforseo

Warn

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the user to execute an opaque setup script located at ./extensions/dataforseo/install.sh.
  • [COMMAND_EXECUTION]: The skill calls a local Python utility script scripts/dataforseo_costs.py to handle budget checks and logging, which involves executing shell commands with dynamic arguments.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests large amounts of untrusted data from external search results and YouTube comments, which could contain malicious instructions.
  • [INDIRECT_PROMPT_INJECTION]: Ingestion points: Tools such as serp_organic_live_advanced, serp_youtube_video_comments_live_advanced, and on_page_content_parsing retrieve content from public websites.
  • [INDIRECT_PROMPT_INJECTION]: Boundary markers: There are no instructions for the agent to use delimiters or ignore potentially malicious content within the retrieved search data.
  • [INDIRECT_PROMPT_INJECTION]: Capability inventory: The skill environment allows for local script execution and file system access for logging.
  • [INDIRECT_PROMPT_INJECTION]: Sanitization: No filtering or validation mechanisms are mentioned to sanitize data before it is processed by the AI agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 28, 2026, 12:50 AM