improve-prompt

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions for prompt optimization. It does not perform any file system operations, network requests, or command execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill's core function is to process user-provided text. While this constitutes an indirect prompt injection surface, the risk is minimal as the skill lacks high-privilege capabilities and explicitly instructs the agent to only return text and not execute the requests.
  • [NO_CODE]: No scripts or executable files are associated with this skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 12:17 PM
Security Audit — agent-trust-hub — improve-prompt