Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看内置样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Security audit
住房公积金汇缴与基数核对（免费版）
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local housing-fund table checker with no evidence of network use, persistence, credential access, or hidden behavior.
Install only if you intend to process housing-fund or payroll contribution table text locally. Review outputs before relying on them, because the skill explicitly does not provide legal or policy compliance advice and does not verify current local housing-fund rules.
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 (6)
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看内置样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Ae1
High
- Category
- analysis-evasion
- Content
node scripts/run.mjs --sample # 先看内置样例
- Confidence
- 100% confidence
- Finding
- Referenced artifact was not completely inspected
Natural-Language Policy Violations
Low
- Confidence
- 87% confidence
- Finding
- The primary display name is presented only in Chinese, and the skill content is predominantly framed for Chinese-language interaction without any user-facing statement that users may choose their preferred language. Although an English metadata field exists elsewhere, the natural-language description does not clearly offer language selection or opt-in.
Intent-Code Divergence
Low
- Confidence
- 91% confidence
- Finding
- The comment says non-JSON input will be treated as plain-text material such as a '合同全文' (full contract text), which contradicts the rest of the file's stated purpose of checking housing-fund monthly contribution detail tables. The code itself just passes the text through to the housing-fund engine, so the documentation suggests a broader document type than the skill actually claims to support.
Natural-Language Policy Violations
Low
- Confidence
- 88% confidence
- Finding
- The JSON contains only Chinese headers, values, and notes in the sample text, which indicates a fixed locale/language presentation. For a general template file, this can violate language/locale policy when no opt-in, alternative locale, or justification is provided.
Static analysis
No suspicious patterns detected.