Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample # 先看样例
Security audit
医保结算清单与DRG入组核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local Chinese DRG settlement table checker that reads user-provided files and does not show hidden network, persistence, or credential behavior.
Install only if you need a Chinese-language, local checker for DRG settlement reconciliation tables. It processes sensitive medical and payment data locally from files you provide, so review inputs before use and do not treat its output as a substitute for hospital coding,医保办, or local policy review.
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 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
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/run.mjs --sample # 先看样例
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The file’s user-facing comments, instructions, and result strings are entirely in Chinese, including required input guidance and output notes. There is no indication that the skill is region-specific by policy or that users may choose another language, which creates a natural-language locale constraint without opt-in.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The inline documentation says non-JSON input is treated as plain text material, giving '直接粘贴的合同全文' as an example. That contradicts this skill's stated purpose and surrounding code, which consistently expects a 医保结算清单与DRG入组核对表 with headers rather than arbitrary contract text. This is an intent-level documentation mismatch, even though the actual behavior remains local file/text processing.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
This JSON file embeds all user-facing text in Chinese, including headers and medical/payment terminology, with no indication that the skill is region-specific or that users can opt into this locale. Under the policy, forcing a specific language without user choice or clear justification is a natural-language policy concern.
- Content