Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 跑 `node scripts/run.mjs --sample` 会打印本次实际执行的检查项。**本免费版不执行**下面这 5 项
Security audit
校车运行与安全检查记录核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local school-bus record checker with disclosed limits and no evidence of hidden network, persistence, or destructive behavior.
Install only if you are comfortable running a local Node script over school-bus records and using a Chinese-header table format. The tool does not verify official records online and its free version intentionally omits several safety checks, so its output should be treated as a record-consistency aid rather than a compliance determination.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 跑 `node scripts/run.mjs --sample` 会打印本次实际执行的检查项。**本免费版不执行**下面这 5 项
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 跑 `node scripts/run.mjs --sample` 会打印本次实际执行的检查项。**本免费版不执行**下面这 5 项
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 跑 `node scripts/run.mjs --sample` 会打印本次实际执行的检查项。**本免费版不执行**下面这 5 项
Lp1
High
- Category
- MCP Least Privilege
- Confidence
- 75% confidence
- Finding
The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The file’s natural-language contract, warnings, and user-facing messages are written entirely in Chinese, and the parser only recognizes Chinese labels and allowed result values. There is no opt-in, fallback, or documented justification that this skill is limited to a Chinese-speaking or China-specific deployment context.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 98% confidence
- Finding
The file's natural-language interface, help text, status messages, and usage guidance are entirely in Chinese, with no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The inline comment says non-JSON input is treated as plain-text material, giving the example '直接粘贴的合同全文' (full contract text). That contradicts this skill's documented intent of checking school-bus operation and safety inspection records, because it describes handling an unrelated document type.
- Content