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
工程进度款与产值确认核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local, disclosed checker for Chinese engineering progress-payment tables and does not show hidden network, credential, persistence, or destructive behavior.
Install only if you need a local checker for Chinese progress-payment/output-value confirmation tables. It does not appear to send data out or modify files, but users should still review the line-cited results manually because the tool only checks table arithmetic and explicitly does not validate construction completion, approvals, contract legality, or other business/legal facts.
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
- 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
- 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
- 95% confidence
- Finding
- The file’s natural-language interface, examples, labels, error messages, and usage guidance are all written in Chinese, and required input columns are recognized only via Chinese header keywords. There is no indication that users may choose another language or that the locale restriction is explicitly documented as a region-specific requirement.
Natural-Language Policy Violations
Low
- Confidence
- 83% confidence
- Finding
- The main description and trigger instructions are provided in Chinese, which can impose a language expectation on users. Although an English description field exists, the activation guidance and core user-facing details here do not explicitly offer a language choice or opt-in.
Natural-Language Policy Violations
Low
- Confidence
- 92% confidence
- Finding
- The only natural-language content in this JSON template is a fixed Chinese table header and row labels, which imposes a specific language/locale. There is no indication that the user can opt into another language or that the locale restriction is explicitly justified as region-specific.
Static analysis
No suspicious patterns detected.