The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run commands via npx webcrawl, including scrape, extract, and map. This involves executing code in the agent's shell environment.\n- [EXTERNAL_DOWNLOADS]: The use of npx involves downloading the webcrawl package from the NPM registry at execution time.\n- [INDIRECT_PROMPT_INJECTION]: The skill crawls external websites and uses an LLM-based extraction process to normalize job data. This creates a surface for indirect prompt injection where malicious content on a career page could attempt to influence the agent's behavior.\n
Ingestion points: External career page URLs (e.g., Greenhouse, Lever, Workable, Ashby) accessed via the scrape and extract commands.\n
Boundary markers: No specific delimiters or safety warnings are present in the extraction prompts provided in the skill.\n
Capability inventory: The skill has the ability to execute shell commands (npx) and interact with the filesystem (storing datasets in jobs.json or CSV).\n
Sanitization: There is no evidence of sanitization or content filtering of the scraped HTML/Markdown content before it is passed to the LLM for extraction.

webcrawl-jobs-leads