prompt-rewriter
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: No malicious patterns, hardcoded credentials, or unauthorized network operations were detected in the skill instructions or metadata.- [PROMPT_INJECTION]: The skill processes untrusted user prompts as primary input for its rewriting service, which is a standard functional surface for indirect prompt injection.
- Ingestion points: User-provided prompts intended for analysis and rewriting (SKILL.md).
- Boundary markers: Absent; the skill does not define explicit delimiters for the input text.
- Capability inventory: Zero; the skill does not request or use any tools for file system access, network communication, or code execution.
- Sanitization: Absent; the skill relies on the underlying model's inherent safety filters to handle content within input prompts. Because the skill lacks external capabilities, the risk associated with this surface is negligible.- [NO_CODE]: The skill does not include or execute any external scripts, binaries, or dependencies, operating purely as a set of behavioral instructions for the AI agent.
Audit Metadata