Back to skill

Security audit

产业链上下游图谱·逐条挂源

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated suspicious because scanners report that its documented supply-chain mapping purpose does not match parts of its behavior, and its setup instructions use an unpinned installer and send an API key to a catalog-selected endpoint.

Consider avoiding installation until you have reviewed the remote endpoint and credential handling, confirmed what information may be sent to external services, and checked the installed content. The scan found meaningful concerns but was partial, so it does not provide a complete safety assessment.

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
  • 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
Findings (13)

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · README.en.md (reported line 34)May include surrounding context.

bash
CATALOG="https://cuecue.cn/api/mcp-catalog"
curl -s "$CATALOG" | python3 -c 'import json,sys
rows=json.load(sys.stdin)["data"]["domains"]
[print(r.get("id"), r.get("external_status"), (r.get("routing") or {}).get("url", "-")) for r in rows]'
DOMAIN_ID="<replace with a domain id listed by the line above>"

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · README.en.md (reported line 38)May include surrounding context.

md
rows=json.load(sys.stdin)["data"]["domains"]
[print(r.get("id"), r.get("external_status"), (r.get("routing") or {}).get("url", "-")) for r in rows]'
DOMAIN_ID="<replace with a domain id listed by the line above>"
ROUTING_URL="$(curl -s "$CATALOG" | python3 -c 'import json,sys
rows=json.load(sys.stdin)["data"]["domains"]
hit=[r["routing"]["url"] for r in rows if r.get("id")==sys.argv[1] and r.get("routing")]
print(*hit,sep="\n") if hit else sys.exit("not found: that id is not in the live catalog (or it has no routing.url) - run the listing line first, then fill it in")' "$DOMAIN_ID")"

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · README.md (reported line 34)May include surrounding context.

bash
CATALOG="https://cuecue.cn/api/mcp-catalog"
curl -s "$CATALOG" | python3 -c 'import json,sys
rows=json.load(sys.stdin)["data"]["domains"]
[print(r.get("id"), r.get("external_status"), (r.get("routing") or {}).get("url", "-")) for r in rows]'
DOMAIN_ID="<把这里换成上一行列出的那个域 id>"

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · README.md (reported line 38)May include surrounding context.

md
rows=json.load(sys.stdin)["data"]["domains"]
[print(r.get("id"), r.get("external_status"), (r.get("routing") or {}).get("url", "-")) for r in rows]'
DOMAIN_ID="<把这里换成上一行列出的那个域 id>"
ROUTING_URL="$(curl -s "$CATALOG" | python3 -c 'import json,sys
rows=json.load(sys.stdin)["data"]["domains"]
hit=[r["routing"]["url"] for r in rows if r.get("id")==sys.argv[1] and r.get("routing")]
print(*hit,sep="\n") if hit else sys.exit("未取到:该 id 不在目录现值里(或它没有 routing 里的 url 字段)——先跑上面那行列出现场的 id 再填")' "$DOMAIN_ID")"

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied code is a template generator, not an implementation of the declared supply-chain mapping capability. It uses the subject only in introductory text and processes source metadata solely for validation and listing. Its own output explicitly states that supply-chain structure is missing. Source validation and local file operations are ordinary supporting details, and the code does respect the prohibition on investment judgments, but these do not resolve the material gap between an evidence-backed map and an unfilled skeleton. No unrelated network access or other undeclared sensitive behavior is evident.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied chunk does not retrieve supply-chain evidence, identify companies or supply-chain positions, attach sources, or report missing links. Its implemented workflow is remote service discovery and authenticated tool listing. Such discovery could support a larger research implementation, but this chunk establishes no connection between the selected service and the declared supply-chain task. The credential transmission is observable behavior, not evidence by itself of credential theft.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
89% confidence
Finding

所给代码的实际功能是发现 MCP 服务并列举其工具,没有接收行业或公司作为分析对象,也没有调用资料检索工具、生成三层产业链或输出来源引用。工具发现可以是支持性步骤,但该片段没有建立所选域或工具与声明任务的联系,且会向目录返回的端点发送认证凭据;声明未体现这种通用服务发现和认证访问行为。此判断仅针对所提供片段,不意味着代码存在恶意行为或已发生凭据泄露。

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The installation command invokes an unpinned npm CLI and retrieves skill content without an immutable revision. Although this is an installer rather than an MCP server, upstream compromise or unexpected updates could introduce code or agent instructions into the local environment.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
97% confidence
Finding

The command sends CUE_API_KEY to a URL copied directly from a remote catalog without validating its scheme or destination. Authentication is relevant to the documented research integration, but a compromised or misconfigured catalog could redirect the credential to an attacker-controlled endpoint or an unencrypted HTTP destination.

Content

Scanner excerpt · README.en.md (reported line 43)May include surrounding context.

md
hit=[r["routing"]["url"] for r in rows if r.get("id")==sys.argv[1] and r.get("routing")]
print(*hit,sep="\n") if hit else sys.exit("not found: that id is not in the live catalog (or it has no routing.url) - run the listing line first, then fill it in")' "$DOMAIN_ID")"
[ -n "$ROUTING_URL" ] || { echo "no value: ROUTING_URL is empty - list the ids first, then set DOMAIN_ID to one of them" >&2; exit 1; }
curl -s -X POST "$ROUTING_URL" \
  -H "Authorization: Bearer $CUE_API_KEY" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' \

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

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The installation command runs an unpinned npm CLI and installs skill content without an immutable revision. This creates a supply-chain exposure to unexpected upstream changes, even though the scanner incorrectly describes the CLI as an MCP server.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
97% confidence
Finding

The bearer credential is transmitted to a destination taken verbatim from a live catalog, without an HTTPS requirement or an independently enforced origin restriction. This is legitimate integration setup in context, but catalog compromise or misconfiguration could expose the credential to an unauthorized recipient.

Content

Scanner excerpt · README.md (reported line 43)May include surrounding context.

md
hit=[r["routing"]["url"] for r in rows if r.get("id")==sys.argv[1] and r.get("routing")]
print(*hit,sep="\n") if hit else sys.exit("未取到:该 id 不在目录现值里(或它没有 routing 里的 url 字段)——先跑上面那行列出现场的 id 再填")' "$DOMAIN_ID")"
[ -n "$ROUTING_URL" ] || { echo "取值失败:ROUTING_URL 为空——先跑上面那行列出现场 id,再把 DOMAIN_ID 换成其中之一" >&2; exit 1; }
curl -s -X POST "$ROUTING_URL" \
  -H "Authorization: Bearer $CUE_API_KEY" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' \

The online workflow uses external retrieval and parsing services without warning about disclosure of source materials or document URLs.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The documented workflow includes external parsing of URLs and local files but does not establish a disclosure warning or authorization gate for sending their contents to the service. Public announcements reduce the usual sensitivity, but user-supplied material or signed document URLs could contain confidential information; approval of spending does not establish approval of disclosure.

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.