The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions mandate the use of a local script dataforseo_costs.py via the claude-seo command runner. This script is used to estimate, approve, and log API costs, representing a legitimate security and budget control feature rather than a malicious execution pattern.- [EXTERNAL_DOWNLOADS]: The documentation references an installation script at ./extensions/dataforseo/install.sh. This is a local path within the extension's installation directory and does not involve downloading code from unknown external sources.- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from various external sources, including search results, YouTube comments, and third-party LLM outputs (via ai_optimization_chat_gpt_scraper).
Ingestion points: Tools like serp_organic_live_advanced, serp_youtube_video_comments_live_advanced, and on_page_content_parsing fetch external content.
Boundary markers: The instructions do not define specific delimiters or warnings to ignore embedded instructions in the ingested data.
Capability inventory: The agent has the capability to execute local scripts via claude-seo run.
Sanitization: No explicit sanitization or filtering of external content is described in the prompt instructions.

seo-dataforseo