liubang-perspective
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes user-provided queries to generate responses in a specific persona.\n
- Ingestion points: User questions processed by the liubang-perspective agent as defined in SKILL.md.\n
- Boundary markers: Absent. The skill does not explicitly define delimiters to separate user input from the persona instructions.\n
- Capability inventory: The skill is restricted to text-based interaction and lacks file-system access, network operations, or shell command execution capabilities across its scripts and documentation.\n
- Sanitization: Absent. User input is interpolated directly into the response generation process without filtering or validation.\n- [EXTERNAL_DOWNLOADS]: The README provides an installation command using npx to fetch the skill from the vendor's resource repository.
Audit Metadata