Back to skill

Security audit

公司一页纸

Security checks for vulnerabilities and agentic risk

Overview

The skill is marked suspicious because scanners report that it can send an API key to a destination from an external catalog, has behavior that does not match its stated company overview purpose, and includes an unpinned installer; the analysis is partial despite scanning all listed components.

Consider avoiding installation until the credential destination and the MCP discovery behavior are independently reviewed and shown to be necessary for the stated task. Treat the installer’s unpinned version as an additional supply-chain risk. Coverage is incomplete: Skillspector marked its analysis partial because some local references could not be resolved, while AIG completed with no findings; neither result proves the skill safe or establishes malicious intent.

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 (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 50)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 54)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 50)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 54)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

该代码块的直接功能是 MCP 服务发现、路由选择和认证工具枚举,并未体现公司识别、财务提取、事件及风险核查或五段速览生成。虽然工具发现可以成为实现业务功能的辅助步骤,但这里没有将所选服务或所列工具与声明的公司速览任务关联起来,且域标识可手动选择。因此,就提供的代码而言,其主要行为和资源访问范围与声明用途存在实质差异。代码未显示调用具体业务工具或执行深研,也不足以断言存在恶意外传。

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The supplied chunk performs service discovery and authenticated API probing. It does not accept a company identifier, retrieve company disclosures or financial statements, check events or risks, or construct the specified report. Tool discovery could support a larger research implementation, but this chunk establishes no such connection. Its externally determined credential destination is also not explained by the declared purpose. This assessment does not establish malicious intent or credential theft.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The installation command invokes an unpinned npm CLI through npx and installs skill content from a repository without an immutable revision. Although this is not an MCP server declaration, the supply-chain concern is real: a compromised or unexpected future release could execute installer code or introduce malicious agent instructions.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

The command sends CUE_API_KEY to a URL taken directly from a remote catalog without checking its scheme or authorized destination. Authentication is legitimate for this workflow, but a compromised or misconfigured catalog could direct the bearer token to an attacker-controlled server or an unencrypted HTTP endpoint.

Content

Scanner excerpt · README.en.md (reported line 59)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
95% confidence
Finding

The quick-start command executes an unpinned npm CLI through npx and retrieves skill content without an immutable repository revision. This is a supply-chain weakness rather than an MCP server configuration issue, because changed upstream code or skill instructions could run with the installer's or agent's privileges.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

The bearer credential is attached to a routing URL accepted verbatim from the external catalog, with no scheme or destination authorization checks. While the request supports the declared data-channel setup, a malicious or erroneous catalog entry could disclose the key to an unauthorized recipient or transmit it over HTTP.

Content

Scanner excerpt · README.md (reported line 59)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"}' \

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

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 opinion validator accepts filled-in opinions when they follow a [待人工] prefix, contradicting the documented empty-placeholder requirement.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The validator uses prefix matching for opinion placeholders, so a line such as - [待人工] 公司盈利能力持续改善 counts as an empty placeholder and is not rejected as additional opinion content. In a financial tear-sheet skill that explicitly reserves opinions for humans, this lets generated or attacker-supplied commentary pass validation and appear in a supposedly compliant document; the banned-word filter does not catch all substantive opinions.

Content

No source excerpt is available for this finding.