Back to skill

Security audit

Industry Daily Brief

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious, with medium confidence, mainly because it reports weak safeguards around public deployment and broad access to files and networks; the scan was partial.

Consider the reported email certificate-verification weakness and public report exposure before installing, especially if you will send reports or deploy them to GitHub Pages. Check that the skill's file and network access matches what you intend to allow. The scan is incomplete: 16 of 17 components were scanned, with partial inspection of one, so these results do not establish that the skill is safe.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/send_email.py
Finding

SMTP authentication uses TLS without certificate verification

Content
View full analysis

Impact

The attacker can capture SMTP credentials and report contents, potentially enabling unauthorized email submission.

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/deploy_github.py
Finding

Public deployment bypasses the documented content-approval gate

Content
View full analysis

Impact

If the selected draft contains confidential or unpublished information, it can become publicly accessible and remain in repository history after the current page is replaced.

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
Findings (26)

Tainted flow: 'req' from os.environ.get (line 92, 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/deploy_github.py (reported line 94)May include surrounding context.

python
req = urllib.request.Request(url, data=body, headers=headers, method=method)
    try:
        with urllib.request.urlopen(req, context=ctx) as resp:
            return json.loads(resp.read().decode("utf-8")), resp.status
    except urllib.error.HTTPError as e:
        err_body = e.read().decode("utf-8")

Tainted flow: 'req' from os.environ.get (line 94, 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/send_dingtalk.py (reported line 95)May include surrounding context.

python
data = json.dumps(payload, ensure_ascii=False).encode("utf-8")
    print(f"  长度: {len(content)} 字符")
    req = urllib.request.Request(webhook_url, data=data, headers={"Content-Type": "application/json; charset=utf-8"}, method="POST")
    with urllib.request.urlopen(req) as resp:
        result = json.loads(resp.read().decode("utf-8"))
        print(f"  errcode: {result.get('errcode')}, errmsg: {result.get('errmsg')}")
        return result

Tainted flow: 'req' from os.environ.get (line 103, 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/send_dingtalk.py (reported line 104)May include surrounding context.

python
payload = {"msgtype": "link", "link": {"title": title, "text": text, "messageUrl": message_url, "picUrl": ""}}
    data = json.dumps(payload, ensure_ascii=False).encode("utf-8")
    req = urllib.request.Request(webhook_url, data=data, headers={"Content-Type": "application/json; charset=utf-8"}, method="POST")
    with urllib.request.urlopen(req) as resp:
        result = json.loads(resp.read().decode("utf-8"))
        print(f"  [链接] errcode: {result.get('errcode')}")
        return result

Tainted flow: 'req' from os.environ.get (line 79, 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/send_discord.py (reported line 81)May include surrounding context.

python
print(f"  大小: {len(data)} 字节")
    req = urllib.request.Request(webhook_url, data=data, headers={"Content-Type": "application/json; charset=utf-8"}, method="POST")
    try:
        with urllib.request.urlopen(req) as resp:
            print(f"  [推送] 状态: {resp.status}")
    except urllib.error.HTTPError as e:
        print(f"  [失败] HTTP {e.code}: {e.read().decode('utf-8')[:300]}")

Tainted flow: 'req' from os.environ.get (line 96, 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/send_discord.py (reported line 98)May include surrounding context.

python
body += file_data + f"\r\n--{boundary}--\r\n".encode("utf-8")
    req = urllib.request.Request(webhook_url, data=body, headers={"Content-Type": f"multipart/form-data; boundary={boundary}"}, method="POST")
    try:
        with urllib.request.urlopen(req) as resp: print(f"  [上传] 状态: {resp.status}")
    except urllib.error.HTTPError as e: print(f"  [上传失败] {e.code}")

def main():

Tainted flow: 'req' from os.environ.get (line 109, 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/send_feishu.py (reported line 110)May include surrounding context.

python
data = json.dumps(payload, ensure_ascii=False).encode("utf-8")
    print(f"  长度: {len(md_content)} 字符")
    req = urllib.request.Request(webhook_url, data=data, headers={"Content-Type": "application/json; charset=utf-8"}, method="POST")
    with urllib.request.urlopen(req) as resp:
        result = json.loads(resp.read().decode("utf-8"))
        print(f"  code: {result.get('code', result.get('StatusCode', -1))}")
        return result

Tainted flow: 'req' from os.environ.get (line 131, 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/send_feishu.py (reported line 132)May include surrounding context.

python
if ts: payload["timestamp"] = ts; payload["sign"] = sign
    data = json.dumps(payload, ensure_ascii=False).encode("utf-8")
    req = urllib.request.Request(webhook_url, data=data, headers={"Content-Type": "application/json; charset=utf-8"}, method="POST")
    with urllib.request.urlopen(req) as resp:
        result = json.loads(resp.read().decode("utf-8"))
        print(f"  [卡片] code: {result.get('code', -1)}")
        return result

Tainted flow: 'req' from os.environ.get (line 98, 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/send_slack.py (reported line 100)May include surrounding context.

python
print(f"  长度: {len(text)} 字符")
    req = urllib.request.Request(webhook_url, data=data, headers={"Content-Type": "application/json; charset=utf-8"}, method="POST")
    try:
        with urllib.request.urlopen(req) as resp:
            print(f"  [推送] 响应: {resp.read().decode('utf-8')}")
    except urllib.error.HTTPError as e:
        print(f"  [失败] HTTP {e.code}: {e.read().decode('utf-8')}"); sys.exit(1)

Tainted flow: 'req' from os.environ.get (line 90, 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/send_teams.py (reported line 92)May include surrounding context.

python
print(f"  大小: {len(data)} 字节")
    req = urllib.request.Request(webhook_url, data=data, headers={"Content-Type": "application/json; charset=utf-8"}, method="POST")
    try:
        with urllib.request.urlopen(req) as resp:
            result = resp.read().decode("utf-8")
            print(f"  [推送] {'成功' if result == '1' or resp.status in (200,202) else result[:100]}")
    except urllib.error.HTTPError as e:

Tainted flow: 'req' from os.environ.get (line 109, 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/send_telegram.py (reported line 111)May include surrounding context.

python
data = json.dumps(payload, ensure_ascii=False).encode("utf-8")
    req = urllib.request.Request(f"{TG_API}/bot{token}/sendMessage", data=data, headers={"Content-Type": "application/json; charset=utf-8"}, method="POST")
    try:
        with urllib.request.urlopen(req) as resp:
            r = json.loads(resp.read().decode("utf-8"))
            print(f"  ok: {r.get('ok')}, msg_id: {r.get('result',{}).get('message_id','N/A')}")
            return r

Tainted flow: 'req' from os.environ.get (line 131, 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/send_telegram.py (reported line 133)May include surrounding context.

python
body += file_data + f"\r\n--{boundary}--\r\n".encode("utf-8")
    req = urllib.request.Request(f"{TG_API}/bot{token}/sendDocument", data=body, headers={"Content-Type": f"multipart/form-data; boundary={boundary}"}, method="POST")
    try:
        with urllib.request.urlopen(req) as resp:
            print(f"  [文件] ok: {json.loads(resp.read().decode('utf-8')).get('ok')}")
    except urllib.error.HTTPError as e: print(f"  [上传失败] {e.code}")

Tainted flow: 'req' from os.environ.get (line 552, 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/send_wecom.py (reported line 557)May include surrounding context.

python
headers={"Content-Type": "application/json; charset=utf-8"},
        method="POST"
    )
    with urllib.request.urlopen(req) as resp:
        result = json.loads(resp.read().decode("utf-8"))
        print(f"  [摘要] errcode: {result.get('errcode')}, errmsg: {result.get('errmsg')}")
        return result

Tainted flow: 'req' from os.environ.get (line 590, 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/send_wecom.py (reported line 582)May include surrounding context.

python
headers={"Content-Type": f"multipart/form-data; boundary={boundary}"},
        method="POST"
    )
    with urllib.request.urlopen(req) as resp:
        result = json.loads(resp.read().decode("utf-8"))
        media_id = result.get("media_id")
        print(f"  [上传] errcode: {result.get('errcode')}, media_id: {media_id}")

Tainted flow: 'req' from os.environ.get (line 590, 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/send_wecom.py (reported line 595)May include surrounding context.

python
headers={"Content-Type": "application/json; charset=utf-8"},
            method="POST"
        )
        with urllib.request.urlopen(req) as resp:
            result = json.loads(resp.read().decode("utf-8"))
            print(f"  [文档] errcode: {result.get('errcode')}, errmsg: {result.get('errmsg')}")

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · README.md (reported line 203)May include surrounding context.

md
| `SMTP_USER` | SMTP username | When using email |
| `SMTP_PASSWORD` | SMTP password | When using email |
| `EMAIL_TO` | Recipients (comma-separated) | When using email |
| `GITHUB_TOKEN` | GitHub Personal Access Token | When using GitHub |
| `GITHUB_USER` | GitHub username | When using GitHub |

## 🔌 Channel Setup Guides

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · README_zh.md (reported line 203)May include surrounding context.

md
| `SMTP_USER` | SMTP 用户名 | 使用邮件时 |
| `SMTP_PASSWORD` | SMTP 密码 | 使用邮件时 |
| `EMAIL_TO` | 收件人(逗号分隔) | 使用邮件时 |
| `GITHUB_TOKEN` | GitHub Personal Access Token | 使用 GitHub 时 |
| `GITHUB_USER` | GitHub 用户名 | 使用 GitHub 时 |

## 🔌 各渠道快速配置指南

Code capability 'file_read' detected in scripts/deploy_github.py but not covered by declared permissions.

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'file_read' capability that is not covered by the declared 'allowed-tools' preapproval. Review the host runtime's actual enforcement policy; runtime permissions are unknown unless separately verified, and this declaration alone does not establish a permission ceiling.

Content

No source excerpt is available for this finding.

Code capability 'network' detected in scripts/deploy_github.py but not covered by declared permissions.

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'network' capability that is not covered by the declared 'allowed-tools' preapproval. Review the host runtime's actual enforcement policy; runtime permissions are unknown unless separately verified, and this declaration alone does not establish a permission ceiling.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/deploy_github.py (reported line 11)May include surrounding context.

python
python deploy_github.py 2026-03-10          # 部署指定日期的日报

环境变量:
  GITHUB_TOKEN       — GitHub Personal Access Token(需要 repo 权限)
  GITHUB_USER        — GitHub 用户名
  GITHUB_REPO        — 目标仓库名(默认 data-ai-daily)
"""

Code capability 'file_write' detected in scripts/init_config.py but not covered by declared permissions.

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'file_write' capability that is not covered by the declared 'allowed-tools' preapproval. Review the host runtime's actual enforcement policy; runtime permissions are unknown unless separately verified, and this declaration alone does not establish a permission ceiling.

Content

No source excerpt is available for this finding.

Mandatory pre-flight checks require English section titles without a user language choice.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The documented mandatory pre-flight requires generated briefs to have English section titles and sends failures back for regeneration. This imposes a specific output language without documenting user opt-in or a justified locale constraint.

Content

No source excerpt is available for this finding.

The automatic trigger “Create a daily report for 2026-03-10” does not specify an industry-news briefing.

Medium
Category
Trigger Abuse
Confidence
90% confidence
Finding

A request to create a daily report could refer to a work log, sales summary, or other unrelated report. The README says this request automatically triggers the full pipeline but supplies no exclusion conditions to distinguish those requests from industry-intelligence briefings.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 232)May include surrounding context.

md
<details>
<summary><b>🌍 Slack</b></summary>

1. Visit https://api.slack.com/apps → Create New App
2. Features → Incoming Webhooks → Enable
3. "Add New Webhook to Workspace" → select channel
4. **Copy Webhook URL** → set `SLACK_WEBHOOK_URL`

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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_zh.md (reported line 232)May include surrounding context.

md
<details>
<summary><b>🌍 Slack</b></summary>

1. 访问 https://api.slack.com/apps → Create New App
2. Features → Incoming Webhooks → 开启
3. "Add New Webhook to Workspace" → 选择目标频道
4. **复制 Webhook URL** → 配置到 `SLACK_WEBHOOK_URL`

The GitHub Pages deployment instructions omit a warning that published reports may be publicly accessible.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The standalone deployment example does not warn that GitHub Pages can make a report accessible beyond its intended team. Public-news inputs reduce the default risk, but customized reports can contain internal analysis or accidentally included sensitive material, making an undisclosed change in audience consequential.

Content

No source excerpt is available for this finding.