ClawHub
Back to skill

Security audit

AI Notes of Video

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims: it sends a user-provided video URL to Baidu's AI-notes API and queries the result, with no hidden persistence or local data access found.

Install only if you are comfortable sending video URLs and referenced video content to Baidu's Qianfan service using your BAIDU_API_KEY. Avoid internal, signed, private, or sensitive media URLs unless that data sharing is approved.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill asks for a user-supplied video URL and states that Baidu downloads and parses the video, but it does not clearly warn that the URL and referenced content will be sent to a third-party service for processing. This creates a real privacy and data-handling risk because users or agents may submit sensitive, internal, or signed URLs without informed consent, potentially exposing proprietary media or embedded access tokens to Baidu.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% 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 · scripts/ai_notes_task_create.py (reported line 16)May include surrounding context.

python
params = {
        "url": video_url,
    }
    response = requests.post(url, headers=headers, json=params)
    response.raise_for_status()
    result = response.json()
    if "code" in result:

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This code sends the user-supplied video URL to an external Baidu API using an authenticated HTTP request. While the script's purpose is API interaction, there is no visible disclosure in comments, docstrings, or user-facing output that the input URL and associated request metadata will be transmitted to a third-party service.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description and surrounding documentation describe a video-to-AI-notes skill, but L07 labels it 'AI PPT Generation'. This is reinforced later by the mismatched API label 'PPTOutlineGenerate API' for a task-query operation, creating active contradiction in the file's intent documentation rather than mere omission.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

L45 introduces a 'PPTOutlineGenerate API', but the parameter and example clearly correspond to querying an AI notes task result using ai_notes_task_query.py and a task ID. This is an intent/documentation contradiction that could mislead users about what capability the skill exposes.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

The script implements a query operation against /ai_note/query and expects a task_id argument, but the usage string says python ai_notes_task_create.py <url>. This is an active contradiction in inline documentation because it names a different script/action (create) and a different parameter type (url) than the code actually uses.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.