Back to skill

Security audit

募集资金使用与募投进度·逐条挂源

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill suspicious with high confidence because scanners report behavior that conflicts with its offline ledger purpose, including network discovery and local usage tracking; some analysis was incomplete.

Consider the suspicious verdict before installing. The reported conflicts with the offline promise and unrelated local usage tracking are material; also, coverage was partial, with 14 of 16 components fully inspected and parser limitations affecting two. The scanners do not establish malicious intent, and their evidence does not show financial records or credentials being transmitted.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (32)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
90% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · CHANGELOG.md (reported line 54)May include surrounding context.

md
- **为什么要有它:** 平台的两个下载计数器都不可信——新 listing 上架首 48 小时会一次性播种 50~60 的初始计数,那不是用户下载。本地这枚文件是本件唯一能证明「真有人装上并跑过」的证据。
- **规矩:** `try/except` 全包,任何失败静默跳过——不报错、不改退码、不吐杂音。同一天跑多次只留一枚。
- 清掉:`rm -rf ~/.cue-usage`。

**零通道骨架**(`scripts/make_outline.py`,零网络、零计费、不依赖任何通道产物):

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
90% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · README.en.md (reported line 128)May include surrounding context.

md
**It never gets in the way:** any failure (read-only home, full quota, no `HOME`) is skipped silently — no error, no exit-code change, not a single line of noise. Running it several times in one day still leaves one file.

To clear it: `rm -rf ~/.cue-usage`.

---

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
90% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · README.md (reported line 128)May include surrounding context.

md
**它不会碍事:** 任何失败(家目录只读、配额满、无 HOME)都静默跳过,不报错、不改退码、不吐一句杂音。同一天跑多次只留一枚。

要清掉:`rm -rf ~/.cue-usage`。

---

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
85% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · CHANGELOG.md (reported line 54)May include surrounding context.

md
- **为什么要有它:** 平台的两个下载计数器都不可信——新 listing 上架首 48 小时会一次性播种 50~60 的初始计数,那不是用户下载。本地这枚文件是本件唯一能证明「真有人装上并跑过」的证据。
- **规矩:** `try/except` 全包,任何失败静默跳过——不报错、不改退码、不吐杂音。同一天跑多次只留一枚。
- 清掉:`rm -rf ~/.cue-usage`。

**零通道骨架**(`scripts/make_outline.py`,零网络、零计费、不依赖任何通道产物):

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
85% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · README.md (reported line 128)May include surrounding context.

md
**它不会碍事:** 任何失败(家目录只读、配额满、无 HOME)都静默跳过,不报错、不改退码、不吐一句杂音。同一天跑多次只留一枚。

要清掉:`rm -rf ~/.cue-usage`。

---

YARA rule 'agent_skill_destructive_autonomous_actions': Autonomous destructive filesystem, shell history, or repository actions in AI agent skills [agent_skills]

High
Category
YARA Match
Confidence
75% confidence
Finding

YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).

Content

Scanner excerpt · README.en.md (reported line 116)May include surrounding context.

md
bad samples one by one / line-by-line substitution on the good sample as a positive-and-negative control. The last line reports `档数=3|不合=N|不可判=N`.

The tests cover the shell contract — `--help` exits 0, no argument exits 2, missing file exits 3, `--demo` output passes its own checker and is byte-reproducible, an empty listing emits no shell, and the beacon lands while failing silently.

---

## 8. First-run beacon

After argument parsing succeeds and before any real work, the entry scripts drop an **empty file** at `~/.cue-usage/<slug>-<date>`.

**Why:** both platform download counters are unreliable — a new listing is seeded with 50–60 initial counts in its first 48 hours, and that is not people downloading. This local file is the only evidence this piece has that someone actually installed it and ran it.

**It never gets in the way:** any failure (read-only home, full quota, no `HOME`) is skipped silently — no error, no exit-code change, not a single line o

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
90% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · README.en.md (reported line 128)May include surrounding context.

md
**It never gets in the way:** any failure (read-only home, full quota, no `HOME`) is skipped silently — no error, no exit-code change, not a single line of noise. Running it several times in one day still leaves one file.

To clear it: `rm -rf ~/.cue-usage`.

---

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
85% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · README.en.md (reported line 128)May include surrounding context.

md
**It never gets in the way:** any failure (read-only home, full quota, no `HOME`) is skipped silently — no error, no exit-code change, not a single line of noise. Running it several times in one day still leaves one file.

To clear it: `rm -rf ~/.cue-usage`.

---

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The clearest mismatch is mark_first_run(), which runs after successful argument parsing, including for --selftest and invocations missing a listing. It creates a directory and dated marker in the user's home directory and silently suppresses failures. This installation/use tracking is unrelated to ledger preparation and is not disclosed by the declared purpose. The outline generation itself is relevant supporting functionality, so this helper alone cannot establish that the broader skill lacks the promised ledger workflow; however, those substantive capabilities are not demonstrated in this chunk. The zero-network claim is consistent with the code: URLs are validated and printed, not fetched.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The advertised offline workflow includes explicit external HTTP requests and remote MCP discovery. The problem is the contradictory network boundary, not evidence of secret exfiltration or malicious tool execution.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The description promises zero network access, but the workflow directs the agent to fetch an external catalog and contact a catalog-selected MCP endpoint. This can cross an offline execution boundary without informed approval and introduce untrusted remote responses, although the requests shown do not transmit ledger contents or credentials.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The document forbids independently calculated ratios but later describes accepting them when marked 〔自算〕 with numerator and denominator provenance. This inconsistency can let unsupported financial progress figures receive apparent validation; the separate local-tracking allegation is not evidenced within this source.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill promises zero networking while directing requests to an external API and a dynamically selected routing URL. That discrepancy undermines informed authorization and permits remote interaction in an ostensibly offline workflow.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The zero-network declaration conflicts with the supplied curl workflow for remote catalog retrieval and tool discovery. Although these operations are disclosed in the body, a user selecting an offline financial-data skill could still authorize it under an inaccurate capability description.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

Most tests support the declared offline ledger workflow. However, the FirstRunBeacon tests explicitly require a separate usage-recording side effect outside ledger inputs and outputs: an empty marker identifying the skill and execution day, deduplicated within that day. This tracking is not disclosed and is not necessary for ledger generation or validation. The implementation of marker creation is not included, so the chunk establishes the required behavior rather than independently proving its implementation. No network transmission or credential access is shown; local markers do not contradict the zero-network claim.

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 139)May include surrounding context.

md
bash scripts/fixtures/run_fixtures.sh # 三档离线自检,零网络零计费

Env Variable Harvesting

High
Category
Data Exfiltration
Confidence
60% confidence
Finding

Code enumerates, copies, or searches environment variables for secrets. Bulk environment access can collect credentials unrelated to the skill's stated purpose.

Content

Scanner excerpt · tests/test_raised_funds.py (reported line 32)May include surrounding context.

python
def run(*args, env=None, cwd=None):
    e = dict(os.environ, PYTHONDONTWRITEBYTECODE="1")
    if env:
        e.update(env)
    return subprocess.run([sys.executable, "-B", str(args[0]), *map(str, args[1:])],

The optional channel-verification commands make external network requests despite the manifest's zero-network claim.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The optional verification procedure contacts an external catalog and routing endpoint despite the advertised zero-network boundary. Although it sends no financial documents or credentials, following it exposes connection metadata and violates an offline user's reasonable expectations; its optional labeling limits the risk.

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 150)May include surrounding context.

CATALOG="https://cuecue.cn/api/mcp-catalog" curl -s "$CATALOG" | head -c 2000

take the group's routing address from the catalog, then 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"}'

text

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.en.md (reported line 95)May include surrounding context.

CATALOG="https://cuecue.cn/api/mcp-catalog" curl -s "$CATALOG" | head -c 2000

take the group's routing address from the catalog, then 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"}'

text

The documented workflow makes external HTTP requests despite the manifest's zero-network promise.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The documented channel check makes external HTTP requests despite the skill's zero-network promise. It does not transmit report contents, but it exposes connection metadata and can breach an expected offline boundary; being optional reduces the severity.

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.md (reported line 150)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,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

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 102)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

The workflow makes external network requests despite the manifest's explicit zero-network claim.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The channel section directly instructs external catalog discovery and a POST to a returned routing address, conflicting with the advertised zero-network boundary. An agent following this workflow could make unexpected outbound connections, though these particular requests contain no financial records or credentials.

Content

No source excerpt is available for this finding.

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

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.