The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the orth CLI tool to execute commands against external APIs (Tavily, Scrapegraph, Exa) for site mapping, web scraping, and search tasks. This behavior is consistent with the skill's stated purpose of SEO analysis.
[PROMPT_INJECTION]: The skill processes untrusted data from external websites via the scrapegraph API in SKILL.md. This represents a surface for indirect prompt injection, where malicious instructions embedded in a target website's content could attempt to influence the agent's logic.
Ingestion points: Content is retrieved from external URLs using orth api run scrapegraph /v1/smartscraper.
Boundary markers: No explicit delimiters or boundary markers are defined in the provided workflow to separate external content from system instructions.
Capability inventory: The agent can execute further API calls via the orth tool based on analysis results.
Sanitization: There is no evidence of sanitization or filtering of the scraped content before it is processed by the agent.

seo-analyzer