Back to skill

Security audit

公开信息预尽调清单

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious with high confidence: scanners report credential-routing and installation risks, plus mismatches between its declared company-risk research purpose and some reported behavior; analysis was partial.

Consider not installing until the credential destination and redirect concerns, purpose mismatch, and incomplete analysis are reviewed. If you proceed, review the installation source and version, avoid sending credentials or sensitive research context to destinations you have not independently verified, and do not treat this partial scan as assurance that unexamined behavior 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (35)

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 58)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 62)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
98% confidence
Finding

The supplied chunk is an MCP service-discovery and authenticated tool-listing example. It does not process company or date inputs, collect disclosure evidence, generate the declared tables, or perform the described integrity checks. External tool discovery could support a broader research workflow, but this snippet establishes no connection between the selected services and that workflow, and its demonstrated primary behavior is materially different. The credential transmission is observable, but the snippet alone does not establish malicious intent or credential theft.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

该代码没有接收公司、基准日、回看窗口或用途档位,也没有生成七列风险表、九类覆盖率表或执行所述八道机检。连通性检测可能是更大工作流的辅助步骤,但当前描述未说明这项工具目录发现和凭据认证功能,所给代码也未展示它与风险核查流程的衔接,因此存在实质性的描述—行为不匹配。带凭据的 POST 需要显式开启并经过目标检查,不能据此直接认定为恶意窃取;同时,不带 --post 仍会默认发起匿名目录 GET,并非完全不联网。

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
91% confidence
Finding

The supplied chunk implements an authenticated MCP connectivity/discovery workflow rather than the declared risk-reporting workflow. It does not accept company, reference-date, lookback-window, or use-case inputs, retrieve risk disclosures, build the promised tables, or perform the stated validations. Tool discovery could support such a workflow, but this chunk does not establish that relationship or restrict the selected domain to relevant sources. The credential is sent to the catalog-provided endpoint; the snippet does not establish malicious intent or credential theft. This assessment concerns the supplied chunk, not any unseen implementation.

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 36)May include surrounding context.

md
> 契约权威=本包 `CONTRACT.md`(内部契约的对外派生镜像);验收题单由外部评审工作区维护、不随本包发布——本包**自带成品样与 runner,复现性以 `scripts/fixtures/run_fixtures.sh` 为准**(逐题 1:1、题数与真码集由外部对账表维护、不随本包发布)。

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 184)May include surrounding context.

md
必过、41 必拦,CJK 与中英混排各测)。**控制样的族名与枚数不写进本文**——题单以行内代码点名它出过的控制,生成器据此核「点名即在盘」,实际枚数由 `run_fixtures.sh` 现跑报出(活计数只有一处权威来源:枚数不进本文,避免文档与夹具两处各说一套)。

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 189)May include surrounding context.

md
bash scripts/fixtures/run_fixtures.sh # 全量;退出码非 0=有不符

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 190)May include surrounding context.

md
bash scripts/fixtures/run_fixtures.sh bad-B14 # 单样

Subject attribution is accepted from anywhere in an anchor-containing snapshot, rather than from the anchored record.

High
Category
Excessive Agency
Confidence
99% confidence
Finding

The checker finds snapshots containing an anchor, concatenates their entire contents, and accepts subject attribution if the company name or code appears anywhere in those contents. In a multi-record snapshot, an unrelated record can therefore supply the subject identity for another company's anchored disclosure, allowing misattributed risk facts to pass without rewriting the evidence or its hashes.

Content

No source excerpt is available for this finding.

The credential-destination guarantee does not cover automatic redirects.

High
Category
Excessive Agency
Confidence
99% confidence
Finding

The destination guard checks only the initial URL, while urllib.request.urlopen automatically follows supported redirects and can retain the Authorization header when constructing the redirected request. An approved endpoint that is compromised or exposes a suitable redirect could therefore send the API key to an unapproved host, potentially even over HTTP, despite the initial HTTPS and suffix checks.

Content

No source excerpt is available for this finding.

Chaining Abuse

High
Category
Tool Misuse
Confidence
75% confidence
Finding

Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.

Content

Scanner excerpt · scripts/fixtures/run_fixtures.sh (reported line 29)May include surrounding context.

sh
# 本 runner 绝不删那里任何不是我建的东西(`DD_OUTER_TMP` 只为那条判据与注入反证可见)。
DD_OUTER_TMP="${TMPDIR:-/tmp}"; export DD_OUTER_TMP
RUNTMP="$WORK/tmp"
mkdir -p "$RUNTMP" || { echo "FAIL 建不起 runner 私有临时根 $RUNTMP(环境故障,不续跑不假绿)"; rm -rf "$WORK"; exit 1; }
export TMPDIR="$RUNTMP"
if ls -A "$DD_OUTER_TMP" >/dev/null 2>&1; then
  tmp_before="$(cd "$DD_OUTER_TMP" && ls -A | sort)"; tmp_snap_ok=1

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

Medium
Category
MCP Rug Pull
Confidence
87% confidence
Finding

The documented command npx skills add huhoo/cue-awesome --skill dd-checklist can download and execute an unpinned npm CLI, allowing a compromised future release to run with the invoking user's permissions. This is a CLI supply-chain risk rather than an unversioned MCP server reference; its placement in a historical changelog reduces immediate exposure, but readers may still copy the installation command.

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 invokes an unpinned npm CLI and installs skill content from a mutable repository reference. A compromised upstream release or repository could therefore introduce code or agent instructions with the user's privileges; this is a supply-chain weakness, not evidence of an intentionally malicious MCP server.

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 command runs an unpinned skills CLI and retrieves a mutable skill collection. Describing the collection as official does not prevent an upstream compromise from supplying harmful code or 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 individual data-skill installation command leaves both the installer version and repository revision unpinned. An upstream compromise could replace a credential-handling dependency with malicious content, making this particularly relevant to the subsequent API-key setup.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
99% confidence
Finding

The shell example attaches CUE_API_KEY to a destination taken directly from remote catalog data, checking only that the URL is nonempty. A compromised catalog could select an attacker-controlled HTTPS endpoint or an HTTP endpoint and expose the key; the separately described Python helper's destination checks do not protect this shell command.

Content

Scanner excerpt · README.en.md (reported line 67)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 installation command executes an unpinned npm CLI and installs skill content without an immutable repository revision. Upstream compromise could introduce executable code or malicious agent instructions under the user's authority.

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 mutable installer and repository versions. Official-source attribution does not eliminate the risk that an upstream compromise distributes harmful code or instructions across the installed collection.

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 individual data-skill installation leaves the CLI version and skill revision unpinned. Because this dependency participates in authenticated data access, a substituted upstream version could compromise credentials or agent behavior.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
99% confidence
Finding

The shell command sends the bearer key to a catalog-selected URL without validating its scheme or authorized hostname. Catalog manipulation could redirect the credential to an attacker or expose it over HTTP, and the security gates described for a different helper are absent from this executable example.

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.