Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
安全教育培训记录与签到核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local Chinese-language checker for safety-training records, and its code matches that purpose without network use, credential access, persistence, or hidden behavior.
Install only if you are comfortable running a local Node-based checker on copied safety-training table text. It does not appear to send data out or persist anything, but its interface is Chinese and one duplicate-record summary sentence is imprecise, so review duplicate findings against the detailed row-level messages.
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
- Content
node scripts/run.mjs --sample # 先看样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
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.
Natural-Language Policy Violations
Medium
- Confidence
- 92% confidence
- Finding
- This code file contains extensive natural-language instructions, descriptions, and outputs that assume Chinese-language use. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation unless the constraint is explicitly documented and justified as region-specific.
Description-Behavior Mismatch
Medium
- Confidence
- 96% confidence
- Finding
- The manifest and top-level documentation say the free engine performs '同一人 + 同一培训主题 + 同一培训日期 重复登记检测', and the implementation in checkDuplicateRecords reports the second occurrence as a duplicate. However, the emitted summary basis states such records '只应有两条以内的记录', which semantically permits up to two entries and therefore misdescribes actual behavior.
Intent-Code Divergence
Medium
- Confidence
- 97% confidence
- Finding
- The code comment/docs around the duplicate check describe '同一人 + 同一培训主题 + 同一培训日期 重复登记', and the function at L405-L425 flags any repeated key after the first one. But the user-facing basis string says the same combination may have '两条以内' before being considered duplicate, which actively contradicts the implemented logic.
Natural-Language Policy Violations
Medium
- Confidence
- 93% confidence
- Finding
- The user-facing description, help text, errors, and output strings are entirely in Chinese, with no indication that language is selectable or that the skill is intentionally limited to Chinese-speaking users. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.
Natural-Language Policy Violations
Low
- Confidence
- 85% confidence
- Finding
- This JSON file embeds all visible text in Chinese, including headers and notes, which can amount to a language/locale constraint in the skill content. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy concern.
Static analysis
No suspicious patterns detected.