The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions leverage curl to perform network operations, interacting with Apify's API to initiate and monitor job scraping tasks.
[EXTERNAL_DOWNLOADS]: The skill fetches structured job data from third-party Apify actors: automation-lab/linkedin-jobs-scraper and borderline/indeed-scraper. These actors aggregate content from LinkedIn and Indeed.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted job listings and descriptions from external websites, creating a potential surface for indirect prompt injection attacks where malicious instructions could be embedded in job data.
Ingestion points: Job search results (including descriptions and titles) retrieved from the Apify API (SKILL.md).
Boundary markers: Absent. The workflow does not specify delimiters or instructions to treat the ingested external content as untrusted data.
Capability inventory: The skill utilizes curl for network access to external APIs and includes functionality to write processed results to local CSV files (SKILL.md).
Sanitization: Absent. There is no requirement or implementation described for validating, filtering, or escaping the scraped content before it is presented to the user or saved to disk.

job-scraper