Back to skill

Security audit

或有事项与承诺事项·逐条挂源

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because scanners report undeclared external service activity and persistent local usage tracking that raise privacy and scope concerns.

Consider the suspicious verdict and the reported privacy and scope concerns before installing, especially if you may provide nonpublic financial documents. The AIG scan completed without findings, but Skillspector reports partial analysis: all listed components were scanned, while one local reference could not be resolved, so the evidence is not fully complete.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
Findings (23)

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 148)May include surrounding context.

md
**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 those are not users. This local file is the only evidence that someone actually installed and ran the piece.

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

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

---

## 9. Files

| File | Purpose |
|---|---|
| `SKILL.md` / `SKILL.en.md` | Chinese and English skill descriptions and checker contract |
| `scripts/check_contingency.py` | five checks; `--selftest` runs fixtures, `--demo` prints a sample |
| `scripts/fixtures/` | one good sample, one bad sample, three-tier runner |
| `tests/test_contingency.py` | package tests (entry contract, zero input, beacon) |

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 150)May include surrounding context.

md
**It never gets in the way:** any failure (read-only home directory, full quota, no HOME) is skipped silently — no error, no change to the exit code, not a word of noise. Running several times in one day 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 151)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
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 150)May include surrounding context.

md
**It never gets in the way:** any failure (read-only home directory, full quota, no HOME) is skipped silently — no error, no change to the exit code, not a word of noise. Running several times in one day 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 150)May include surrounding context.

md
**It never gets in the way:** any failure (read-only home directory, full quota, no HOME) is skipped silently — no error, no change to the exit code, not a word of noise. Running several times in one day 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.md (reported line 151)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`。

---

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

该代码执行的是远程服务目录查询和 MCP 工具发现,没有展示财报读取、附注信息提取、事项分类或原文引用登记行为。声明中未说明这些网络资源或工具发现能力,片段也未体现其与财报处理的必要联系,因此属于未声明且与所述用途不一致的行为。

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The reported persistent usage-marker writes are unrelated to constructing or checking the financial register and are not disclosed as a side effect in this skill's operational contract. They create a limited local privacy and unexpected-write concern, not evidence of high-impact exfiltration; the actual script is not supplied here, so the precise invocation paths remain unverified.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

代码没有读取财报、提取或有事项或承诺事项,也没有生成附带原句和锚点的登记表。其可见行为是外部服务目录查询与工具发现,且没有展示这些工具与财报分析任务的关联,因此不能仅视为已声明功能的支持性实现细节。该片段仅枚举工具,未显示实际调用工具或上传财报内容。

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The reported HOME/.cue-usage markers persist usage information outside the task's input and output locations without an explicit tracking opt-in in this source. This is a low-impact privacy and side-effect issue; nothing in the supplied skill establishes that the markers are transmitted or contain document contents.

Content

No source excerpt is available for this finding.

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_contingency.py (reported line 31)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:])],

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_contingency.py (reported line 134)May include surrounding context.

python
os.chmod(td, 0o700)

    def test_no_home_is_silent(self):
        e = dict(os.environ, PYTHONDONTWRITEBYTECODE="1")
        e.pop("HOME", None)
        r = subprocess.run([sys.executable, "-B", str(CHECK), "--demo"],
                           capture_output=True, text=True, env=e, cwd=str(PKG))

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 52)May include surrounding context.

bash
CATALOG="https://cuecue.cn/api/mcp-catalog"
curl -s "$CATALOG" | head -c 2000
curl -s -X POST "$ROUTING_URL" \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

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 53)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

The attachment-parsing workflow lacks a warning that document contents are sent to an external service.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The attachment workflow invokes a server-backed parsing service without explicitly warning that user-provided document contents may leave the local environment or requiring authorization for that disclosure. Public filings reduce the usual confidentiality impact, but screenshots, annotated reports, or nonpublic attachments could contain sensitive information; configuring an API key does not itself authorize uploading every document.

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.

The workflow sends attachments to an external parsing service without warning about disclosure of document contents.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The workflow initiates external parsing when evidence resides in an attachment, but does not clearly warn that document contents will be disclosed to another service or require authorization for that transfer. Although the intended material is generally public filings, user-supplied files and screenshots may include confidential annotations or nonpublic information.

Content

No source excerpt is available for this finding.

Creates persistent usage-tracking files unrelated to financial-note validation.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The validator unconditionally creates dated usage markers under ~/.cue-usage without user consent, including during demo, self-test, and invalid-input runs. This introduces persistent filesystem changes unrelated to financial-note validation and exposes a local history of skill usage; the supplied code does not transmit these markers or financial data.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · tests/test_contingency.py (reported line 34)May include surrounding context.

python
e = dict(os.environ, PYTHONDONTWRITEBYTECODE="1")
    if env:
        e.update(env)
    return subprocess.run([sys.executable, "-B", str(args[0]), *map(str, args[1:])],
                          capture_output=True, text=True, env=e, cwd=str(cwd or PKG))

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · tests/test_contingency.py (reported line 136)May include surrounding context.

python
def test_no_home_is_silent(self):
        e = dict(os.environ, PYTHONDONTWRITEBYTECODE="1")
        e.pop("HOME", None)
        r = subprocess.run([sys.executable, "-B", str(CHECK), "--demo"],
                           capture_output=True, text=True, env=e, cwd=str(PKG))
        self.assertEqual(r.returncode, 0)
        self.assertEqual(r.stderr, "", f"无 HOME 不许吐杂音:{r.stderr[:200]}")

The documented entry script creates a persistent usage beacon unrelated to financial-note extraction or validation.

Low
Category
Excessive Agency
Confidence
95% confidence
Finding

The documented checker creates persistent usage records outside the workspace without an explicit opt-in, although financial-note validation does not require them. This is a limited privacy and filesystem-side-effect concern: the marker reveals the skill and execution date, but the supplied text provides no evidence of remote reporting or financial-document capture.

Content

No source excerpt is available for this finding.

Home-directory resolution contradicts the explicit claim that environment variables are not read.

Low
Category
Excessive Agency
Confidence
99% confidence
Finding

The module documentation at L003 explicitly promises 不读环境变量 (no environment-variable reads). However, os.path.expanduser("~") at L143 consults home-directory environment variables on standard Python platforms, including HOME on Unix, and is reached through the unconditional tracking call at L686.

Content

No source excerpt is available for this finding.

The tests require persistent usage tracking unrelated to financial-report analysis.

Low
Category
Excessive Agency
Confidence
94% confidence
Finding

These tests invoke the checker and require it to create an empty, skill-specific marker under HOME/.cue-usage, deduplicated by day. Although the tests redirect HOME to temporary directories, the behavior they enforce is persistent usage tracking, which is neither disclosed nor necessary for extracting and checking contingency and commitment disclosures.

Content

No source excerpt is available for this finding.