daangn-jobs-search

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill performs network operations to fetch data from www.daangn.com. This is limited to public job listings and does not involve accessing or transmitting sensitive local files or credentials.
  • [PROMPT_INJECTION]: The skill processes untrusted external data from job postings, which constitutes an indirect prompt injection surface. This is assessed as safe because the skill lacks dangerous capabilities that could be exploited via this surface.
  • Ingestion points: Job listing data is fetched from Daangn URLs in scripts/daangn_jobs.py.
  • Boundary markers: None are employed to isolate external data from the prompt.
  • Capability inventory: The skill can only perform HTTP requests and print to stdout; it cannot execute shell commands, write to the filesystem, or evaluate code.
  • Sanitization: The script applies basic HTML unescaping to the retrieved data.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 04:06 PM