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
网点运费与代收货款结算核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local Chinese courier-settlement checker whose code matches its stated purpose and does not show hidden network, persistence, or destructive behavior.
Use this only for exported settlement/COD table text you are comfortable processing locally. Expect Chinese output, verify the arithmetic against original business records, and note that the free version intentionally does not perform the listed withheld checks.
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 (7)
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
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
Natural-Language Policy Violations
Medium
- Confidence
- 84% confidence
- Finding
- The primary display name is presented only in Chinese, and the document content is overwhelmingly Chinese-language despite an English name/description field existing in metadata. This can violate a language/locale policy if users are not given an explicit opt-in or choice of language for the skill experience.
Natural-Language Policy Violations
Medium
- Confidence
- 91% confidence
- Finding
- The file’s natural-language comments and user-facing guidance explicitly frame the tool and its outputs in Chinese, and there is no indication that users can opt into another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.
Intent-Code Divergence
Low
- Confidence
- 95% confidence
- Finding
- The inline documentation states that non-JSON input is handled as plain text, giving '直接粘贴的合同全文' as the example. That contradicts the skill's stated purpose and surrounding help text, which are specifically about courier freight settlement sheets and COD detail tables, not generic contract documents.
Natural-Language Policy Violations
Low
- Confidence
- 94% confidence
- Finding
- The file contains only Chinese-language content in the `text` field and provides no indication that language selection is optional or that the skill is intentionally limited to a Chinese locale. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.
Static analysis
No suspicious patterns detected.