job-posting-analysis

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses PreToolUse and PostToolUse hooks to execute internal shell scripts (pre_network_skill_hook.sh, pre_rate_limit_hook.sh, and post_skill_logging_hook.sh) from relative paths (../../../hooks/skills/). These are vendor-provided lifecycle management scripts.
  • [EXTERNAL_DOWNLOADS]: The skill uses the WebFetch tool to retrieve data from various external Applicant Tracking Systems (ATS) and company career pages for tech stack analysis.
  • [PROMPT_INJECTION]: The skill processes untrusted content from job postings and career pages, which represents an indirect prompt injection surface.
  • Ingestion points: External job posting data fetched via WebFetch.
  • Boundary markers: Not present in the processing logic.
  • Capability inventory: Bash, WebFetch, WebSearch.
  • Sanitization: Not present.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 11:36 PM