hiring-demand-analysis

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a bundled bash script (scripts/crawlora.sh) to communicate with the Crawlora API. The script includes robust security measures: it validates the API key format, implements a strict path allowlist for API endpoints, and prevents local file disclosure by forbidding the use of the @ character in query parameters and streaming POST bodies.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process job postings and company descriptions from an external API (api.crawlora.net), which constitutes a vulnerability surface for indirect prompt injection from third-party data.
  • Ingestion points: scripts/crawlora.sh (fetches external job data from the Crawlora API).
  • Boundary markers: None identified in the skill instructions to delimit external content.
  • Capability inventory: Network access and file execution via the bundled script.
  • Sanitization: The shell script provides strong input sanitization for CLI arguments and environment variables, but the agent receives raw external text from the API response for analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 02:43 AM
Security Audit — agent-trust-hub — hiring-demand-analysis