job-description

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses the WebSearch tool to perform research on job roles, KPIs, and industry trends. The gathered information is then synthesized and integrated into the final document templates. This behavior is consistent with the skill's primary purpose of generating data-backed role guides.
  • [COMMAND_EXECUTION]: The skill is configured with access to the Bash tool. In the provided instructions, this capability is intended for general environment management and standard file operations related to document creation and repository maintenance.
  • [DATA_EXFILTRATION]: The skill publishes the completed role guides to an external Supabase database using the mcp__supabase__execute_sql tool. Supabase is a well-known database service, and this operation represents the intended publishing phase of the workflow for the vendor's application.
  • [PROMPT_INJECTION]: The skill handles untrusted external data from web research results. While the instructions do not include specific boundary markers or sanitization logic, the data is intended for informative summaries rather than executable logic.
  • Ingestion points: Web research queries for KPIs and trends in Step 0.3.
  • Boundary markers: Absent for research data interpolation.
  • Capability inventory: Write, Edit, Bash, and mcp__supabase__execute_sql tools are available to the agent.
  • Sanitization: No explicit sanitization or filtering of web search results is defined in the prompt instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 05:06 AM
Security Audit — agent-trust-hub — job-description