Security audit

Douyin Script Writer

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only Douyin script-writing helper whose memory and image-handling behavior is disclosed and aligned with its purpose, though users should be careful with confidential brand materials.

Install only if you are comfortable letting the agent remember brand details, product claims, audience profiles, and preferences for future Douyin script work. Avoid uploading confidential BREF forms unless you first review what will be saved, and ask the agent to omit or delete sensitive fields when needed.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (8)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The activation scope is overly broad because it claims the skill should be used for script writing, brand memory, user preference setting, and image/BREF extraction across many product categories. This can cause the agent to invoke the skill for generic image-upload or preference-storage requests outside the narrow script-writing context, increasing unintended data capture and cross-context handling.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill explicitly states it will remember brand preferences, brand information, and user habits, but provides no user-facing notice about retention, duration, or sensitivity of stored data. In practice, users may disclose proprietary marketing data or personal preferences without understanding that the information will persist and be reused later.
Content: No source excerpt is available for this finding.

Ssd 3

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill encourages persistent collection and reuse of brand data, user preferences, and image-derived information, but does not define minimization boundaries or sensitivity constraints. This creates a broad memory surface where unnecessary or confidential data can accumulate over time and later be reused in unrelated contexts.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The image workflow directs the agent to extract information from uploaded images and store it into brand memory without warning the user that uploaded content may be retained. This is risky because BREF forms and product materials may contain confidential business information, campaign plans, or restricted claims that should not be silently persisted.
Content: No source excerpt is available for this finding.

Ssd 3

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The workflow instructs the agent to extract all fields from uploaded brand forms and store them for later use, which is excessive collection by design. 'All fields' may include confidential business strategy, internal terminology, prohibited claims lists, or other nonessential data that should not be persistently retained wholesale.
Content: No source excerpt is available for this finding.

Ssd 3

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The brand memory section tells the agent to proactively record new brand and product information and reuse it in later conversations, again without clear consent, scope limits, or deletion controls. In this context, the data is likely commercial and sometimes confidential, so persistent proactive capture materially raises privacy and confidentiality risk.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The document is entirely written as mandatory guidance for Douyin scripts in Chinese and does not indicate that other languages are allowed or that the locale restriction is optional. Under the policy, forcing a specific language or locale without user opt-in is a natural-language policy violation unless clearly justified as region-specific.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 86% confidence
Finding: This markdown file presents all guidance exclusively in Chinese, with no opt-in, alternative language, or documented justification for a Chinese-only audience. Under the policy rule for language/locale constraints, forcing a single language without user choice can be a natural-language policy concern.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.