Back to skill

Security audit

终止经营·持有待售与处置对价

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated suspicious because scanners report behavior that does not match its stated financial-reporting purpose, along with concerns about sending documents to an external service; the scan was incomplete.

Consider avoiding installation until the external document-processing and MCP behavior are clearly explained and you can verify where documents and credentials go. The scan covered 75% of components; one file was only partly inspected and one static analysis was degraded, so the evidence is incomplete.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

代码的直接用途是发现 MCP 服务并获取远程工具列表,未包含年报读取、附注数据提取、原句锚定或财务合计核算逻辑。外部服务发现和携带凭据的工具枚举未在声明中披露,且所示代码没有建立这些操作与声明的财务登记任务之间的支持关系,因此构成能力与资源访问不匹配。代码仅请求工具列表,并未显示调用这些工具或进一步处理财务资料。

Content

No source excerpt is available for this finding.

The workflow directs screenshots and scanned documents to an external reader without warning that user-provided content leaves the local environment.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The workflow routes user-supplied screenshots and scanned documents to an external reader without clearly disclosing the upload or requiring consent. This conflicts with the README's local-only framing and could expose confidential financial material, although already-public annual reports would reduce the confidentiality impact.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · README.md (reported line 108)May include surrounding context.

bash
  # ① 匿名取活体清单
  curl -sS https://cuecue.cn/api/mcp-catalog -o /tmp/mcp-catalog.json
  python3 -c "import json;d=json.load(open('/tmp/mcp-catalog.json'));print(d)"

  # ② 带凭据握手取工具表

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read, file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

L100–L101 claim TO-PL/TO-CASH verify quoted amounts against ledger amounts, but neither check performs that comparison.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The comment assigns quote-to-ledger amount verification to TO-PL and TO-CASH, but those checks only compare ledger amounts with other ledger amounts. An altered report can retain authentic-looking quotations while changing amounts consistently enough to pass arithmetic checks, creating false assurance about financial-data integrity.

Content

No source excerpt is available for this finding.