The Agent Skills Directory

[COMMAND_EXECUTION]: The documentation provides commands for the user or agent to execute a local shell script (./extensions/firecrawl/install.sh) to install the required extension. Executing local scripts is a standard setup procedure but requires the user to trust the script's source.
[PROMPT_INJECTION]: The skill is designed to ingest and analyze content from arbitrary external websites via tools like firecrawl_crawl and firecrawl_scrape. This creates a surface for indirect prompt injection where malicious instructions hidden in scraped HTML or markdown could attempt to influence the agent's behavior.
Ingestion points: External data enters the agent context through the outputs of firecrawl_crawl, firecrawl_scrape, and firecrawl_search as described in SKILL.md.
Boundary markers: None. The instructions do not specify the use of delimiters or 'ignore' instructions for the processed content.
Capability inventory: The skill focuses on data retrieval and analysis; no file-writing or subprocess execution capabilities are explicitly defined in this skill's logic, though it interacts with the broader agent environment.
Sanitization: None. There is no mention of sanitizing, escaping, or validating the content retrieved from external URLs before it is processed by the agent.

seo-firecrawl