Back to skill

Security audit

财报深度点评

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because scanners report credentialed requests to catalog-selected services and a redirect risk, capabilities that do not match its stated financial-report drafting purpose.

Consider avoiding installation until the credential destination and redirect behavior are addressed, the service-discovery capabilities are clearly disclosed or removed, and installation versions are pinned. The scan was partial: 72 of 73 components were scanned, with one partially inspected and a tool-misuse analyzer degraded, 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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (29)

Tainted flow: 'req' from os.environ.get (line 188, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/cue_connectivity_check.py (reported line 193)May include surrounding context.

python
code = None
    raw = ""
    try:
        with urllib.request.urlopen(req, timeout=args.timeout) as resp:
            code, raw = resp.status, resp.read().decode("utf-8", "replace")
    except urllib.error.HTTPError as err:
        detail = ""

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 55)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 one of the ids 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 59)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 one of the ids 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 catalog response (or its routing has no url field) - run the line above and pick one of the ids listed")' "$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 59)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 63)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
99% confidence
Finding

The script's primary function is credentialed tool-service connectivity testing, a materially different capability from the declared financial-analysis workflow. Although such connectivity could support a broader data-access workflow, the supplied description does not establish that connection or disclose this credential-handling behavior. The code gates the authenticated POST behind --post and checks the initial destination for HTTPS and an allowed hostname suffix; those safeguards do not remove the capability mismatch. Without --post, it still performs an anonymous catalog GET unless a local catalog file is supplied.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

声明聚焦财报分析写作与特定文稿检查,代码则实现外部 MCP 服务发现和工具枚举;所示片段未体现财报数据处理、八节点评生成或所声明的四类机检。网络目录查询及向动态获取的路由发送认证凭据并非该声明中可识别的辅助实现细节。片段位于 README,不能据此断言已实际执行,但其所展示的操作与声明用途存在明确差异。

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied chunk implements authenticated MCP discovery and tool enumeration, neither of which is described in the declared purpose. Although remote tools could potentially support financial research, this chunk does not establish that connection or retrieve financial disclosures. Its demonstrated purpose and resource access therefore materially differ from the declared drafting and checking workflow. The code shows credential transmission for authentication, but does not by itself establish malicious credential theft.

Content

No source excerpt is available for this finding.

Automatic redirects can forward the API key beyond the documented HTTPS and authorized-host boundary.

High
Category
Excessive Agency
Confidence
99% confidence
Finding

The destination guard validates only the initial URL, while urllib's default redirect handler can follow a POST's 301, 302, or 303 response as a GET and copy its Authorization header to the redirected request. An attacker controlling an allowed endpoint or an exploitable redirect there could therefore send the API key to an unauthorized host or an HTTP destination, bypassing the claimed HTTPS-and-host boundary.

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
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
94% confidence
Finding

The installation command executes an unpinned npm CLI and installs skill content from an unpinned repository revision. Although this is an installer rather than an MCP server reference, compromised or unexpected upstream updates could introduce executable code or adversarial agent instructions.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The collection installation uses an unversioned npm CLI and a mutable skill repository reference. Installing multiple optional skills expands the upstream content that can influence the agent, making unexpected or compromised updates consequential.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

Selecting a single skill reduces installation breadth but does not pin either the npm installer or the repository content. A future upstream change could therefore execute different installer code or introduce malicious agent instructions.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
99% confidence
Finding

The shell example attaches the API key to a catalog-provided URL without validating its scheme or hostname. A compromised or misconfigured catalog could direct the credential to an attacker-controlled endpoint or an unencrypted HTTP endpoint; the separately described helper-script protections do not protect this shell command.

Content

Scanner excerpt · README.en.md (reported line 64)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 catalog response (or its routing has no url field) - run the line above and pick one of the ids listed")' "$DOMAIN_ID")"
   [ -n "$ROUTING_URL" ] || { echo "Fetch failed: ROUTING_URL is empty - run the line above, then set DOMAIN_ID to one of the ids listed" >&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
94% confidence
Finding

The documented installation executes an unpinned npm CLI and retrieves skill content without an immutable repository revision. This is an installation supply-chain weakness rather than an MCP server-version issue, and unexpected upstream changes could affect local code execution or agent behavior.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The collection installation leaves both the CLI version and repository revision mutable. Optional installation and interactive selection do not prevent a compromised upstream release from supplying malicious installer code or skill instructions.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The single-skill command still executes an unversioned npm installer and installs from a mutable repository reference. Naming a specific skill does not guarantee reproducible or previously reviewed content.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
99% confidence
Finding

The shell block forwards the API key to the URL returned by the catalog after checking only that the value is nonempty. Catalog compromise or routing misconfiguration could expose the key to an unauthorized host or plaintext HTTP connection, despite the separate helper script's documented safeguards.

Content

Scanner excerpt · README.md (reported line 68)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: env, file_read, file_write, network.

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.

Local-document parsing lacks a warning about third-party access to document contents.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The local-document workflow obtains permission for Bridge installation or directory expansion but does not explicitly disclose third-party access to document contents. Minimal directory authorization reduces filesystem exposure, but users could still submit confidential investment materials without understanding the remote-processing boundary.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
96% confidence
Finding

The command for installing this skill also uses an unpinned npm CLI and mutable repository content. A future compromise or upstream change could replace the reviewed behavior with executable installer code or malicious skill instructions.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
96% confidence
Finding

The installation command invokes an unpinned npm CLI and retrieves skill content from a mutable repository reference. Although this is not itself an MCP server declaration, a compromised or unexpectedly changed dependency could execute installer code or introduce adversarial agent instructions.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
96% confidence
Finding

The single-skill installation example leaves both the npm CLI version and repository revision unpinned; selecting a skill by name does not make its contents immutable. This creates a supply-chain exposure even though the scanner inaccurately describes the command as an MCP server reference.

Content

No source excerpt is available for this finding.

Documentation claims automatic enforcement of sourced beat/miss judgments that the checker does not implement.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The document claims that the checker mechanically requires a same-line source reference for beat/miss judgments, but that judgment-specific check is absent. Unsupported performance conclusions can therefore pass the gate, creating false assurance in a financial-analysis workflow despite the stated manual-review requirements.

Content

No source excerpt is available for this finding.