seo-dataforseo

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the execution of local scripts for operational tasks. Specifically, it instructs the agent to run ./extensions/dataforseo/install.sh for extension setup and python scripts/dataforseo_costs.py for monitoring API costs.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process a wide variety of untrusted data from external sources, creating an attack surface for indirect prompt injection. 1. Ingestion points: The skill reads search engine results, YouTube video comments, and extracts text from external websites. 2. Boundary markers: There are no explicit instructions to the agent to treat this data as untrusted or to ignore embedded instructions. 3. Capability inventory: The agent context includes the ability to execute shell scripts, run Python scripts, and access the local filesystem. 4. Sanitization: No evidence of sanitization or structural validation is provided for the ingested data before it is processed by the AI.
  • [EXTERNAL_DOWNLOADS]: The skill relies on an installation script to fetch and set up the necessary DataForSEO extension components from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 07:39 AM
Security Audit — agent-trust-hub — seo-dataforseo