prompt-architect

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely instructional, providing high-quality prompt engineering patterns and workflows. No executable code or shell scripts are included.
  • [SAFE]: The workflow involves a research phase using standard agent tools (like web search) to gather domain knowledge, which is appropriate for the skill's intended purpose and does not involve downloading untrusted scripts.
  • [SAFE]: No evidence of prompt injection, obfuscation, or hardcoded credentials was found in the instructions or reference files.
  • [SAFE]: While the skill processes user-provided prompts (representing an indirect injection surface), it is designed as a text-transformation tool with standard boundary markers (XML tags), and no exploitable capability-read/write chains were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 01:01 PM
Security Audit — agent-trust-hub — prompt-architect