The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute local shell and Python scripts for installation and cost tracking.
Evidence: SKILL.md references executing ./extensions/dataforseo/install.sh and python scripts/dataforseo_costs.py for cost estimation and logging.
Context: These scripts are part of the skill's infrastructure but are not included in the provided definition, making their internal logic unverifiable.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external search engines, social media, and AI platforms.
Ingestion points: Data enters the context via serp_organic_live_advanced (search results), serp_youtube_video_comments_live_advanced (user comments), on_page_content_parsing (raw website text), and ai_optimization_chat_gpt_scraper (AI responses).
Boundary markers: The instructions do not define clear delimiters or specify that the agent should ignore instructions embedded within the retrieved SEO data.
Capability inventory: The agent has the capability to execute scripts (dataforseo_costs.py) and perform network operations via the DataForSEO MCP server.
Sanitization: No explicit sanitization or filtering of the retrieved web content is mentioned before it is processed by the agent.

seo-dataforseo