zh-tw
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were identified. The skill is designed for linguistic rewriting and does not use any sensitive tools or access external resources.- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes conversation history and user-provided arguments. However, it lacks the capabilities (network, file, or command tools) to act on malicious instructions effectively.
- Ingestion points: The skill reads from $ARGUMENTS and the conversation history as defined in SKILL.md.
- Boundary markers: No delimiters or isolation markers are defined for the input.
- Capability inventory: The skill is restricted to text generation and does not utilize any external capabilities.
- Sanitization: No input sanitization is performed.
Audit Metadata