Security audit

guaikei·小红书搜爆款

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently fetches public Xiaohongshu data through a disclosed third-party API and saves results locally, with privacy and retention considerations users should understand.

Install only if you are comfortable sending Xiaohongshu keywords or URLs and your GUAIKEI API token to the guaikei.com service. Expect each run to save full JSON results locally in logs/, so delete or protect those files if they contain sensitive business research, search terms, comments, profile links, or xsec_token URLs.

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 (4)

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The activation description is broad enough to trigger on generic account growth, planning, or marketing-review requests whenever Xiaohongshu data might be useful, even if the user did not explicitly ask to search Xiaohongshu. That can cause the agent to over-collect third-party data, invoke external APIs unexpectedly, and expand the skill's scope beyond clear user consent.

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The CLI writes the full comment task output to a local file using a filename derived from the target URL, without any in-file disclosure or consent prompt. If the returned comments contain personal data or sensitive scraping results, this can leave residual data on disk where other local users, backup systems, or unrelated processes may access it.

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The CLI persists the full request and results to disk, including the profile URL and fetched content, without any explicit consent prompt, minimization, or warning about storage. Even if the target profile is publicly accessible, the saved data may contain tracking parameters, account identifiers, or collected content that becomes a local privacy and data-handling risk if logs are shared, retained too long, or stored on multi-user systems.

Missing User Warnings

Medium

Confidence: 78% confidence
Finding: The CLI persists full search output to a local JSON file using a filename derived from user-controlled input (`keyword`) without any explicit opt-in or warning. Even if intended for logging, this can expose potentially sensitive search terms and results on disk, and the skill context makes this more relevant because users may search for private interests, topics, or operational data and not expect local persistence.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: SKILL.md:16