prompt-improver
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Prompt Injection (LOW): The skill is vulnerable to indirect prompt injection (Category 8) because it ingests untrusted data from users or external files to perform its analysis.\n
- Ingestion points: In SKILL.md, the workflow accepts either raw text or a file path as an input argument ([프롬프트 텍스트 또는 파일 경로]).\n
- Boundary markers: The skill lacks explicit boundary markers or instructions to the agent to disregard malicious commands that might be contained within the prompt being analyzed.\n
- Capability inventory: The agent is explicitly instructed in Step 1 of SKILL.md to read the contents of a file if a path is provided.\n
- Sanitization: There is no evidence of input validation to prevent the agent from reading sensitive files (e.g., configuration files or SSH keys) if a malicious path is provided by the user.
Audit Metadata