cn-gaokao-planner
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No executable code, scripts, or external dependencies are included in the skill. The functionality is entirely composed of markdown-based instructions for the AI agent.
- [SAFE]: No network access, sensitive file access, or data exfiltration patterns were detected in the instructions or metadata.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided inputs regarding exam performance and university data.
- Ingestion points: User-provided inputs including province, score, provincial rank, and historical admission data referenced in SKILL.md.
- Boundary markers: Absent. The skill does not define specific delimiters for separating user data from system instructions.
- Capability inventory: None. The skill does not have access to tools, subprocess calls, file-system writes, or network operations.
- Sanitization: Absent. There is no logic provided to sanitize or validate the integrity of user-supplied historical data.
Audit Metadata