Back to skill

Security audit

并购重组进度跟踪·逐条挂源

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill suspicious because scanners report behavior that does not match its stated tracking purpose, including fabricated retrieval dates and undisclosed remote tool discovery; no clear malicious intent is established.

Consider avoiding installation until the retrieval-date behavior and undisclosed remote discovery are explained or corrected. If you proceed, review the install source and version, and confirm what the remote requests send and what file access the host will allow. The scan was partial because two references could not be resolved, 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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 (9)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

该代码的可见行为是远程服务与工具发现,而非公告时间轴整理或本地质量检查。它明确访问外部目录,并尝试查询另一端点的工具列表;这些访问不仅缺乏与所声明业务功能的明确关联,也与“零网络”表述冲突。即使将“零网络”仅理解为对 check_tracker.py 的限定,当前片段的远程 MCP 发现行为仍未在声明中得到说明。

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
91% confidence
Finding

Generating an outline supports the declared tracking purpose, and installation alone is a supporting detail. However, the additional catalog fetch and JSON-RPC tool-discovery request introduce an undisclosed remote-service dependency. The zero-network statement may apply specifically to check_tracker.py rather than the entire skill, but the description still does not disclose this remote discovery behavior. The supplied chunk does not show the promised checker, though its absence from a partial chunk is not itself evidence of a mismatch. No document upload or data exfiltration is demonstrated.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The installation command invokes an unpinned npm executable and installs skill content from a mutable repository reference. Although this is not itself an MCP server declaration, compromised or unexpected upstream updates could introduce code or agent instructions with the user's execution privileges.

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.en.md (reported line 28)May include surrounding context.

md
curl -s "$CATALOG" | head -c 2000

# 3. Confirm the tools are present
curl -s -X POST "$ROUTING_URL" \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

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 28)May include surrounding context.

md
curl -s "$CATALOG" | head -c 2000

# 3. 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"}'

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 · SKILL.md (reported line 93)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,再确认工具在场

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

text

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The installation example uses an unpinned npm CLI and a mutable skill repository reference. This creates a supply-chain exposure: an upstream compromise or unexpected update could execute malicious installer code or supply malicious skill instructions, although the command is not an MCP server declaration.

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.

Source retrieval dates are fabricated from the earliest announcement's disclosure date.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

Every source receives rows[0][0], the earliest announcement's disclosure date, as its retrieval date even though the script performs no retrieval. This creates false provenance in a tracker whose core contract requires accurate source dates; the draft warnings do not identify these apparently complete dates as fabricated.

Content

No source excerpt is available for this finding.