Security audit

douyin录播并自动上传

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for Douyin uploading, but its browser and page checks are too loose and could expose the selected video or trigger account actions outside the intended boundary.

Install only if you are comfortable giving the skill control of a logged-in Douyin Creator browser session. Use a local loopback CDP endpoint only, close unrelated or suspicious tabs before running it, review the selected video path carefully, and expect that publishing may automatically request an SMS verification code.

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 (3)

T09 · Insecure Skill Coding Practices

Error

Location: scripts/upload_to_creator.js:127
Finding: Unsafe substring-based origin validation can disclose a local file to an attacker-controlled page
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/upload_to_creator.js:70
Finding: Arbitrary CDP endpoint permits undeclared external connections
Content: View full analysis
Remediation: View remediation

other

Note

Location: scripts/upload_to_creator.js:239
Finding: Publishing can automatically request an SMS verification code without explicit opt-in
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The example uses --title "作品描述", which implies a specific language for user-facing content. The README does not state that the skill is China-only or that Chinese is required, nor does it offer an explicit language choice, so this can be read as a locale preference baked into the skill guidance.
Content: No source excerpt is available for this finding.