prompt-architect

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill metadata explicitly disables model invocation (disable-model-invocation: true), preventing the agent from calling tools or executing actions within its environment.
  • [SAFE]: All referenced files are local markdown templates (spec-template.md, prompt-template.md, decision-checklist.md) used for formatting text. No external URLs or remote resources are requested.
  • [SAFE]: There are no indicators of prompt injection, data exfiltration, or obfuscation. The instructions focus on improving prompt quality and reducing ambiguity for downstream coding agents.
  • [NO_CODE]: The skill consists entirely of markdown instructions and templates; it contains no scripts, binaries, or automated installation steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 04:09 PM
Security Audit — agent-trust-hub — prompt-architect