ClawHub
Back to skill

Security audit

Backup Douyin Chat

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local Douyin chat backup guide with clear privacy boundaries, though its referenced helper scripts are not included in the inspected artifact.

Install only if you intentionally want an agent to operate a local Douyin chat backup workflow. Expect QR login, local storage of private chat exports, and possible media downloads from Douyin/CDN endpoints; review the missing local tool scripts in your actual installation before use and avoid sharing generated exports, cookies, signed URLs, or keys.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Context Leakage

High
Category
Data Exfiltration
Confidence
85% confidence
Finding

Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

md
- Use the dedicated browser profile. Never request, paste, print, export, or transmit cookies.
- Treat conversation names, messages, media, user IDs, SQLite files, and exports as sensitive.
- Keep generated files under the tool's `private/im-data` directory with owner-only permissions.
- Never upload chat data or send it to a model/service unless the user explicitly requests that separate action.
- State that the extractor uses an undocumented Douyin endpoint that can change or trigger platform risk controls.

## Report the outcome