job-scraper

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill performs network requests to DuckDuckGo (html.duckduckgo.com) and Apify (api.apify.com) to retrieve job postings. These connections are transparently disclosed and target well-known services for the purpose of search functionality.\n- [PROMPT_INJECTION]: The skill processes external job data which represents a surface for indirect prompt injection.\n
  • Ingestion points: scripts/jobs.py fetches job titles, snippets, and descriptions from external web search results and API responses.\n
  • Boundary markers: The gathered data is written into a structured JSON file (jobs.json).\n
  • Capability inventory: The skill utilizes network read operations and local file writing.\n
  • Sanitization: The script includes a strip_tags function that removes HTML tags and unescapes entities from the retrieved content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 08:23 AM
Security Audit — agent-trust-hub — job-scraper