fu-hang
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to drive persona-based conversational responses, which represents a standard indirect prompt injection surface.
- Ingestion points: User input triggers based on keywords defined in
SKILL.mdsuch as "付航", "PASSION", "吗喽", and "单口喜剧之王". - Boundary markers: Absent; there are no specific delimiters or instructions defined to isolate user input from the skill's logic.
- Capability inventory: The skill has no capabilities beyond text generation. It does not utilize subprocesses, network requests, file system writes, or external tools.
- Sanitization: Absent; the skill does not specify any filtering or validation for the content of user messages.
- [SAFE]: No malicious patterns such as command execution, credential theft, obfuscation, or persistence mechanisms were detected. The skill's behavior is consistent with its stated purpose of character role-play.
Audit Metadata