Back to skill

Security audit

债务重组·逐条挂源

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because scanners report undisclosed usage tracking, unrelated external tool-discovery behavior, and a workflow that may send documents to an external parsing service; analysis was partial.

Review before installing. Consider whether the external parsing workflow is suitable for your documents, especially if they contain confidential information, and whether you are comfortable with the local usage marker and external tool-discovery requests. The scan is incomplete: one referenced script was only partially analyzed, so the evidence does not establish that the artifact is safe.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (11)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
90% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · README.md (reported line 164)May include surrounding context.

md
**它不会碍事:** 任何失败(家目录只读、配额满、无 HOME)都静默跳过,不报错、不改退码、不吐一句杂音。同一天跑多次只留一枚。

要清掉:`rm -rf ~/.cue-usage`。

---

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
85% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · README.md (reported line 164)May include surrounding context.

md
**它不会碍事:** 任何失败(家目录只读、配额满、无 HOME)都静默跳过,不报错、不改退码、不吐一句杂音。同一天跑多次只留一枚。

要清掉:`rm -rf ~/.cue-usage`。

---

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The reported daily home-directory usage markers are unrelated to document validation and are not disclosed in this skill's execution contract. They leave a persistent record of skill use without an opt-in, although there is no evidence here of document-content collection or remote telemetry.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

所示代码的实际功能是外部服务发现与工具枚举,而非债务重组信息提取、登记或原文溯源。工具发现可能是某些工作流的辅助步骤,但本代码没有展示这些服务与所声明财务任务之间的联系,因此不能仅将其认定为相关实现细节。该判断不意味着代码存在数据外传或恶意行为;当前片段没有提供此类证据。

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 94)May include surrounding context.

md
坏样各只发它自己那道码,另带反证样证明「去向照抄原句」「禁词只在引文里」不误红;`--demo` 打印一份完整合规样例(零输入可跑)。夹具 runner 在 `scripts/fixtures/run_fixtures.sh`,三档(机检自测/`--demo` 好样自过/好样副本上只破一处须只发 `DR-LINE`),

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 101)May include surrounding context.

md
| `scripts/fixtures/run_fixtures.sh` | 三档离线 runner(零网络、零计费,产物只落临时目录跑完即删) |

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 55)May include surrounding context.

CATALOG="https://cuecue.cn/api/mcp-catalog" curl -s "$CATALOG" | head -c 2000

从目录里取本组的路由地址,确认工具在场

curl -s -X POST "$ROUTING_URL"
-H 'Content-Type: application/json'
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

text

The workflow routes user-supplied documents through a parsing service without warning that their contents may leave the local environment.

Medium
Category
Output Handling
Confidence
89% confidence
Finding

The workflow directs user-supplied financial documents into a parsing channel without clearly explaining the external data transfer or requiring consent. Public disclosures are usually low sensitivity, but user-supplied restructuring materials may contain confidential financial or counterparty information.

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 attachment-parsing workflow lacks a privacy warning about sending document contents to an external service.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The attachment workflow invokes an external parsing service but discusses availability and billing rather than explicitly warning that document contents may leave the environment. Supplying an API key is not informed consent to upload potentially confidential restructuring documents.

Content

No source excerpt is available for this finding.

The checker silently persists usage markers in the user's home directory, unrelated to debt-restructuring document validation.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The checker creates a dated usage marker under ~/.cue-usage during ordinary validation, demo, and self-test invocations, with no opt-out or runtime notice. This unnecessary persistent side effect exposes local usage history, but the code does not transmit it or store document contents.

Content

No source excerpt is available for this finding.