linkedin-job-scraper

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the 'python-jobspy' package from the public PyPI repository.
  • [COMMAND_EXECUTION]: The skill executes a local Python script ('tools/jobspy_scraper.py') and utilizes shell commands for installation and environment setup.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes external job descriptions from LinkedIn and displays them to the agent.
  • Ingestion points: External job listings are ingested via 'scripts/jobspy_scraper.py' and presented for interpretation in the agent workflow.
  • Boundary markers: No delimiters or safety instructions are used when presenting the scraped content to the agent.
  • Capability inventory: The skill environment permits command execution and filesystem access.
  • Sanitization: Scraped job data (titles, descriptions) is presented to the agent without validation or filtering for embedded instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 03:06 PM
Security Audit — agent-trust-hub — linkedin-job-scraper