prompt-improver

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFE
Full Analysis
  • [Indirect Prompt Injection] (SAFE): The skill is designed to process user-provided prompts (ingestion point). While there are no explicit boundary markers or sanitization steps, a capability inventory confirms the skill lacks any dangerous tools such as file system access, network operations, or command execution. Therefore, even if a user provides a malicious prompt, the skill has no mechanism to cause harm.
  • [Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded credentials, or network-bound functions were detected in either SKILL.md or the reference file.
  • [Remote Code Execution] (SAFE): The skill does not include any scripts, package manifests (package.json, requirements.txt), or commands that download and execute external content.
  • [Prompt Injection] (SAFE): The instructions are focused on legitimate prompt engineering techniques and do not contain any patterns intended to bypass AI safety filters or extract system prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 01:20 AM