nestjs-architecture-principles

Pass

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and analyze a target repository's source code, configuration, and manifests to perform architectural changes and execute commands. This creates a surface for indirect prompt injection where malicious instructions embedded in the target code could influence the agent's behavior.
  • Ingestion points: Repository files including package.json, nest-cli.json, TypeScript configurations, bootstrap files, and module/provider source files as specified in SKILL.md.
  • Boundary markers: The skill requires reading coordination contracts and manifests but lacks explicit instructions to treat code comments or data as untrusted or to ignore embedded natural language instructions within those files.
  • Capability inventory: The skill permits the agent to edit files, install packages, generate code, and execute state-changing commands like migrations as described in the pre-execution conflict guard in SKILL.md.
  • Sanitization: The skill implements a conflict guard that requires the agent to stop for clarification if incompatible instructions are identified, providing a manual review checkpoint.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 2, 2026, 11:49 PM
Security Audit — agent-trust-hub — nestjs-architecture-principles