NYC

nestjs-queue-architect

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill identifies external data ingestion points where it reads project architecture files. While this is standard for context-aware coding assistants, instructions embedded in those project files could theoretically influence the agent's output.
  • Ingestion points: SKILL.md (instructions to read .agents/SYSTEM/ARCHITECTURE.md and existing services).
  • Boundary markers: Absent; no explicit instructions to ignore embedded prompts in ingested files.
  • Capability inventory: The skill is restricted to code generation; no subprocess calls, file-write, or network operations were detected across the provided files.
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:02 PM