bullmq-specialist-v2

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: The provided code examples demonstrate best practices for secure configuration by using environment variables (process.env.REDIS_URL) instead of hardcoding sensitive credentials.
  • [EXTERNAL_DOWNLOADS]: The skill references standard, legitimate Node.js packages such as bullmq, ioredis, and @bull-board/api. These are widely-used libraries for job queue management and Redis interaction.
  • [SAFE]: References to external services like Upstash, Redis Cloud, and AWS ElastiCache target well-known and reputable technology providers.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it ingests untrusted user task descriptions and operates within powerful CLI environments (claude-code, codex-cli).
  • Ingestion points: User-provided task descriptions and context strings processed by the BullMQ specialist workflow.
  • Boundary markers: The skill does not implement explicit delimiters or instruction-ignore warnings for processed data.
  • Capability inventory: The associated tools listed in metadata have broad shell and file system access.
  • Sanitization: No input sanitization or verification steps are defined for external data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 10:55 PM
Security Audit — agent-trust-hub — bullmq-specialist-v2