prompt-improver

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's implementation is entirely instructional and does not utilize any code, tools, or external system interactions.
  • [PROMPT_INJECTION]: The instructions are designed to optimize other prompts and do not contain any jailbreak attempts or overrides of the agent's core safety protocols. The usage of keywords like 'IMPORTANT' and 'CRITICAL' in the text refers to prompting techniques rather than malicious instruction overrides.
  • [DATA_EXFILTRATION]: No sensitive data access or exfiltration mechanisms were identified. The skill does not use network or file system tools.
  • [EXTERNAL_DOWNLOADS]: References to external documentation point to an official, well-known platform, which is considered a safe and trusted resource.
  • [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or secrets were found in the skill or its associated reference files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 11:40 PM