Back to skill

Security audit

所有者权益变动·逐条挂源

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill suspicious because scanners report undisclosed external service access and credential use that do not clearly fit its stated financial document task; analysis was also incomplete.

Consider the suspicious verdict and incomplete scan coverage before installing. In particular, avoid using it with private financial documents or credentials unless you understand and trust the external services and how routing destinations are checked.

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 (7)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

所给代码实际执行的是远程 MCP 服务发现与工具枚举,没有读取财报、提取权益变动数据、添加原文锚点或进行勾稽计算。虽然工具发现可能作为某些系统的辅助步骤,但该片段未展示这些服务与声明的财务分析任务之间的关联,且引入了未披露的外部访问及凭据使用,因此构成描述与行为不匹配。

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

所提供代码仅获取并打印远程 MCP 目录,未读取财报、提取权益变动表、生成原文锚点或进行勾稽计算。没有证据表明该目录请求是声明中财务处理流程的必要支持步骤,因此其访问资源与实际行为均与声明用途存在实质不符。代码未显示上传财报或其他本地数据。

Content

No source excerpt is available for this finding.

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 141)May include surrounding context.

md
| `scripts/fixtures/run_fixtures.sh` | 离线样例 runner:自测→好样→坏样三档,坏样注入必先断言落地;期望退码由自测末行的「不可判=N」现算,不写死 |

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

The anonymous catalog request itself sends no financial documents or API key, but the subsequent instructions send CUE_API_KEY to a routing URL obtained from that remote response without specifying destination validation. A compromised catalog or manipulated routing value could therefore redirect the bearer credential to an attacker-controlled endpoint.

Content

Scanner excerpt · README.md (reported line 90)May include surrounding context.

发现先行,匿名取 live 目录,拿到 routing 后再连接发 tools/list,以现场返回为准,不硬编码工具名与工具数:

bash
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.get('routing') or d)"
# 拿到 routing 后,带 token 发 tools/list:
curl -sS -X POST "$ROUTING_URL" -H "Authorization: Bearer $CUE_API_KEY" \

The document-parsing workflow lacks a privacy warning about sending financial documents to an external service.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The workflow directs screenshots and scanned documents to an external parsing service without requiring a confidentiality check or informed authorization. Published reports present limited privacy risk, but user-provided attachments may contain unpublished financial information, annotations, or personal data that would cross an external trust boundary.

Content

No source excerpt is available for this finding.

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.

The workflow sends screenshots and scanned attachments to an external parsing service without a privacy warning.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The skill instructs the agent to send screenshots and scanned attachments through an external parsing channel when the source text is in an attachment, without a privacy warning or confidentiality gate. Although the intended reports are often public, arbitrary user-provided attachments can contain confidential information that users have not authorized an external processor to receive.

Content

No source excerpt is available for this finding.