Security audit

Xiaohongshu Copywriter

Security checks for vulnerabilities and agentic risk

Overview

This is a content-writing helper with no executable code; its main issues are documentation cautions around API keys and originality, not hidden dangerous behavior.

Before installing, treat any Pro API key as a secret credential and use the skill's rewrite feature only to learn general structure, not to copy another creator's text, style, or platform-protected content. The artifact itself shows no executable code or hidden system access.

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 (4)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The README instructs users to configure an API key using a visible command-like example but does not warn that the credential is secret, should not be pasted into chats, committed to files, or shared publicly. In an agent/skill ecosystem, unclear secret-handling guidance increases the chance users expose keys in prompts, screenshots, shell history, or synced config files, which can lead to unauthorized API use.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: SQP-3 applies to all file types and includes language or locale policy violations. The document is framed as an expert for Xiaohongshu copywriting and explicitly says '不要中英混杂（显得不专业）', which imposes a language preference without opt-in or noting that the locale is intentionally China-platform-specific.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill explicitly promotes rewriting existing viral Xiaohongshu posts by extracting their structure and generating new content, but it provides no safeguards about copyright, plagiarism, attribution, or platform policy compliance. In a content-generation context, this omission can encourage users to produce derivative material that infringes creators’ rights or violates platform rules, increasing legal and account-enforcement risk.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 72% confidence
Finding: SQP-3 applies to all file types and includes language or locale policy violations. The entire skill README is presented only in Chinese and targets Chinese-platform content creation, but it does not state that language is optional or user-selectable, which may conflict with an organizational policy requiring language choice unless the locale restriction is justified.
Content: No source excerpt is available for this finding.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: README.md:51