ClawHub
Back to skill

Security audit

AI图文视频理解与生文专家

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for LinkFox text generation, but it needs review because a configurable gateway can receive the API key, user prompts, media URLs, and session metadata without destination validation.

Review this skill before installing in environments with sensitive prompts, private media URLs, or production LinkFox keys. Only run it when LINKFOX_TOOL_GATEWAY is unset or explicitly points to a trusted HTTPS LinkFox gateway, avoid submitting secrets or confidential media unless you accept remote processing, and be aware it may save large outputs locally and chain into other AIGC skills for image/video workflows.

A.I.G

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 (1)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/aigc_textgen.py:73
Finding

Unrestricted Gateway Override Can Exfiltrate API Credentials and User Content

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (7)

Tainted flow: 'req' from os.environ.get (line 333, 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/aigc_textgen.py (reported line 237)May include surrounding context.

python
req = _lf_Request(url, headers={"User-Agent": "LinkFox-Skill/2.0"})
    try:
        with _lf_urlopen(req, timeout=timeout) as resp:
            if guessed_ext == "bin":
                ct = resp.headers.get("Content-Type", "")
                if "mp4" in ct:

Tainted flow: 'req' from os.environ.get (line 333, 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/aigc_textgen.py (reported line 335)May include surrounding context.

python
}
    req = Request(url, data=data, headers=headers, method="POST")
    try:
        with urlopen(req, timeout=HTTP_TIMEOUT) as response:
            return json.loads(response.read().decode("utf-8"))
    except HTTPError as e:
        body = e.read().decode("utf-8") if e.fp else ""

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill clearly documents execution of local Python scripts, polling remote endpoints, use of stdin/stdout, savedPath file output, and chaining into other skills, but it declares no explicit tool scope or permissions. That mismatch increases the risk that an agent can invoke network and file-capable behaviors without transparent consent boundaries or least-privilege controls.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger phrases include very common requests like '帮我写一段', 'AI写作', 'text generation', and '图片识别', which can match ordinary conversations and cause the skill to activate unexpectedly. In this skill, accidental activation is more dangerous because activation can send user text and media URLs to remote APIs and may initiate chained downstream calls to other AIGC skills.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs users to provide prompts and media URLs and describes remote asynchronous API calls, but it does not warn that user text, images, and videos will be transmitted to external model services. This creates a privacy and data-handling risk, especially because users may provide sensitive media or proprietary text without understanding that it leaves the local agent context.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The API documentation shows that prompts, media URLs, and optional member IDs are sent to remote services, but it does not indicate any requirement to notify users, obtain consent, or minimize sensitive data before transmission. In a text/image/video analysis skill, user inputs may contain personal, confidential, or regulated content, so silent external transmission creates a real privacy and compliance 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 · references/api.md (reported line 110)May include surrounding context.

| 10009 | 任务不存在 | 检查 taskId 是否正确 | | 其他 | 业务异常 | 参考 errmsg 字段 |

curl 示例

bash
# 1. 创建任务