Back to skill

Security audit

Douyin Orchestrator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Douyin transcription workflow that saves local outputs, with no packaged executable code or hidden behavior found.

Before installing, expect the skill to use a browser profile to access Douyin, run local media/transcription tools, and save transcripts or optional videos plus index files on disk. Use it only for content you are allowed to download or transcribe, and choose storage locations with the same care you would use for sensitive notes or recordings.

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

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The manifest describes downloading, transcribing, analyzing, and outputting structured results by orchestrating three modules. The file also states a distinct Step 4 that saves artifacts to filesystem locations and updates index files, which is additional state-changing behavior not reflected in the manifest description.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description says the skill orchestrates douyin-fetcher, douyin-transcriber, and douyin-analyzer for video transcription. However, the documented behavior explicitly adds a separate /note/ path using browser snapshot extraction rather than the three-module pipeline, which expands behavior beyond the stated scope.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 52)May include surrounding context.

md
**调用模块**:`douyin-fetcher`

详见 `~/.openclaw/skills/douyin-fetcher/SKILL.md`

⚠️ **注意**:Step 1 的 browser act 调用必须用 `request={"kind": "evaluate", "fn": "..."}` 嵌套格式。

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 64)May include surrounding context.

md
**调用模块**:`douyin-transcriber`

详见 `~/.openclaw/skills/douyin-transcriber/SKILL.md`

⚠️ **注意**:如果 Step 1 下载了 DASH 分离流,直接用 `audio.mp4` 转 WAV 转录,不需要先合并

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 76)May include surrounding context.

md
**调用模块**:`douyin-analyzer`

详见 `~/.openclaw/skills/douyin-analyzer/SKILL.md`

**做法**:转录后由 agent 直接分析(语义分段、修正错误、提取要点)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill documents persistent storage of transcripts, optional video files, and index updates, but the high-level description does not clearly warn users that content will be written to disk and indexed. This can create privacy and consent issues, especially because transcripts may contain sensitive spoken content and saved indexes make retention broader and more discoverable.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.