Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例（样例本身就是一张干净的明细表）
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
票务收入与渠道结算核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This is a local ticket-revenue reconciliation helper that reads user-supplied tables, performs arithmetic checks, and does not show network use, persistence, credential access, or destructive behavior.
Install only if you are comfortable running a local Node-based checker on ticket revenue and channel settlement data. It does not verify real box-office activity, bank receipts, contract terms, or tax treatment, so treat its output as an arithmetic reconciliation aid rather than a financial or legal 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 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（样例本身就是一张干净的明细表）
- 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（样例本身就是一张干净的明细表）
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Natural-Language Policy Violations
Medium
- Confidence
- 80% confidence
- Finding
- The skill’s visible documentation and operational instructions are overwhelmingly presented in Chinese, while the file does not state that usage is limited to Chinese-speaking users or provide an explicit language-choice/opt-in mechanism. Under the policy, a locale or language constraint should be documented and justified or offered as a user choice.
Natural-Language Policy Violations
Medium
- Confidence
- 95% confidence
- Finding
- The file’s natural-language comments, user-facing guidance, messages, and examples are entirely in Chinese, and the skill appears designed to interact with users through those strings. There is no indication that users may choose another language or that the locale restriction is explicitly documented as a justified region-specific requirement.
Natural-Language Policy Violations
Medium
- Confidence
- 96% confidence
- Finding
- This code file contains extensive natural-language strings that define usage, errors, and help text exclusively in Chinese. Under the stated policy, forcing a specific language without offering a user choice or documenting a justified locale restriction is a natural-language policy violation.
Intent-Code Divergence
Low
- Confidence
- 96% confidence
- Finding
- At L075, the comment gives the example '直接粘贴的合同全文' for fallback plain-text handling. The rest of the manifest and file consistently describe this skill as operating on ticket revenue/channel settlement detail tables, not arbitrary contract text, so this inline documentation overstates or misstates the intended material type.
Static analysis
No suspicious patterns detected.