seo-dataforseo

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the user to run a local installation script (./extensions/dataforseo/install.sh) to set up the required MCP server environment. Executing local scripts is a standard requirement for this extension but represents a command execution surface.
  • [EXTERNAL_DOWNLOADS]: The skill relies on external data provided by the DataForSEO service and requires the installation of an external extension/MCP server to function.
  • [PROMPT_INJECTION]: The skill processes untrusted data from external sources, including Google/YouTube search results, channel comments, and scraped AI responses, which could contain adversarial instructions intended to influence the agent's behavior (Indirect Prompt Injection).
  • Ingestion points: Untrusted data enters the context via serp_organic_live_advanced (SERP results), serp_youtube_video_comments_live_advanced (YouTube comments), and ai_optimization_chat_gpt_scraper (ChatGPT output).
  • Boundary markers: The instructions do not specify any delimiters or safety markers to isolate the retrieved external content from the agent's core instructions.
  • Capability inventory: The agent has access to numerous SEO-related MCP tools and is encouraged to execute local scripts during the prerequisite phase.
  • Sanitization: There is no documentation of content sanitization or validation for the data fetched from external APIs.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 01:38 AM