skills/affaan-m/ecc/prompt-optimizer/Gen Agent Trust Hub

prompt-optimizer

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is strictly advisory and includes explicit instructions to never execute the user's task or perform implementation actions such as writing code or running commands.
  • [SAFE]: Project detection (Phase 0) involves reading standard configuration files (like package.json or go.mod) to identify the tech stack. This is a common and legitimate practice for developer tools to provide context-aware recommendations.
  • [SAFE]: No malicious patterns such as prompt injection, obfuscation, or data exfiltration attempts were detected in the instructions or examples.
  • [SAFE]: The skill uses localized analysis of the user's draft prompt and project structure to suggest appropriate workflow components without requesting or using sensitive credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 10:16 AM
Security Audit — agent-trust-hub — prompt-optimizer