Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例（内置样例是一张干净表，应当 0 条发现）
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
会员卡预收与履约负债核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This is a local-only Chinese membership-card ledger checker whose file reading and Bash usage are disclosed and proportionate to its purpose.
Install this only if a Chinese-language local checker for exported membership-card ledger tables fits your workflow. It reads the input file you pass to it and prints findings locally; review the stated free-version limitations before relying on the results for accounting decisions.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- 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 (7)
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看样例（内置样例是一张干净表，应当 0 条发现）
- 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（内置样例是一张干净表，应当 0 条发现）
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Natural-Language Policy Violations
Medium
- Confidence
- 93% confidence
- Finding
- The file’s user-facing natural-language instructions, warnings, and outputs are entirely in Chinese, including the top-level description of what the tool does and how users must provide input. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless a locale constraint is explicitly justified, which is not stated here.
Natural-Language Policy Violations
Low
- Confidence
- 89% confidence
- Finding
- The user-facing description, usage text, errors, and output strings are entirely in Chinese, which effectively constrains interaction to a specific language. The file does not indicate that other languages are supported or that the user can opt into Chinese, so this is a natural-language locale policy concern.
Intent-Code Divergence
Low
- Confidence
- 94% confidence
- Finding
- The inline documentation states that non-JSON input will be handled as plain-text material, 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 consistently require a membership-card sales/redemption detail table with headers, not arbitrary contract text.
Vague Triggers
Low
- Confidence
- 89% confidence
- Finding
- This is a manifest file, so vague-trigger review applies. The only substantive field is a generic "text" blob containing tabular data, and there is no indication of what user request or context should activate the skill, nor any exclusion conditions or trigger boundaries.
Static analysis
No suspicious patterns detected.