The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes vendor-specific CLI tools, specifically anycap crawl and anycap search, to perform web research and site auditing. These commands are used to fetch live data from external websites and search engines to inform SEO recommendations.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, which is a recognized vector for indirect prompt injection attacks.\n
Ingestion points: Data is collected from arbitrary external URLs via the anycap crawl and anycap search commands as described in SKILL.md.\n
Boundary markers: The instructions do not define specific delimiters or boundary markers to ensure that the agent distinguishes between website content and its own operational instructions.\n
Capability inventory: The skill has the capability to execute shell commands (via the anycap CLI) and generate reports based on the data retrieved from external sites.\n
Sanitization: There are no documented procedures for sanitizing, escaping, or filtering the content retrieved from external sources before it is processed by the agent.

anycap-ai-tool-seo