cn-social-insurance-explainer
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is purely informational, providing explanations of social insurance and housing funds in China. It does not perform any dangerous operations such as file system modifications, privilege escalation, or persistence. It does not contain any remote code execution patterns, external downloads, or network requests.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection as it processes and interpolates user-provided data into its output framework.
- Ingestion points: User input regarding their city, monthly wage, and specific life situation as defined in the 'Required Inputs' section of SKILL.md.
- Boundary markers: The skill does not utilize specific delimiters or boundary markers to isolate user-provided data from instructions.
- Capability inventory: The skill's capabilities are limited to text generation and basic mathematical calculations. It lacks access to dangerous tools such as network requests, file system writers, or shell command execution.
- Sanitization: No explicit sanitization or filtering logic is provided in the instructions to handle malicious content in user inputs.
Audit Metadata