Security audit

guaikei-xhs-kol-finder

Security checks across malware telemetry and agentic risk

Overview

This skill coherently retrieves public Xiaohongshu data through a disclosed third-party API, with local result logging that users should be aware of.

Install only if you are comfortable sending Xiaohongshu search terms or target links, along with your GUAIKEI_API_TOKEN, to guaikei.com. Review and delete the generated logs if the collected public content, query history, or research targets should not remain on disk.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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

Findings (6)

Context-Inappropriate Capability

Medium

Confidence: 91% confidence
Finding: The CLI persists fetched results to a local JSON file via log.taskWrite, even though the skill is described as read-only retrieval. Persisting scraped results without an explicit opt-in can expose sensitive operational data, query history, and collected content to other local users, backup systems, or later processes, especially if the results include identifiers or large datasets.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The CLI writes full comment results to a local JSON file after successful execution, but there is no explicit user notice, consent prompt, or opt-out for persistence. Because the tool handles scraped public comments and metadata for KOL analysis, silent retention can create privacy, compliance, and local data exposure risks if the host system is shared or logs are later exfiltrated.

Missing User Warnings

Medium

Confidence: 83% confidence
Finding: The tool sends the user-supplied target URL and API token to an external service to create and fetch a comment task, but it does not clearly warn the user that this data leaves the local environment. Even though external transmission is expected for this skill's purpose, lack of transparency can cause unintended disclosure of targets, usage patterns, or sensitive tokens in environments with stricter data handling requirements.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The CLI writes the full task output, including scraped note/comment data and request metadata, to a local JSON file automatically with no explicit opt-in or warning in this file. Because this skill processes third-party content and potentially sensitive research targets, silent persistence increases the risk of unintended data retention, later disclosure to other local users/processes, or accidental check-in to source control.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The code writes the full result set to disk without clearly warning the user that data will persist beyond terminal output. In a data-collection skill, silent persistence increases privacy and compliance risk because users may assume ephemeral processing while the tool leaves structured artifacts containing collected content and metadata on the host.

Missing User Warnings

Low

Confidence: 89% confidence
Finding: The CLI writes full search results to a local JSON file using a filename derived in part from user-controlled input (`keyword`) without an explicit opt-in or prominent warning at the write site. Even though the data is from public Xiaohongshu content, persisted local copies can expose searched terms, collected content, and operational metadata to other local users, backup systems, or downstream processes, creating an avoidable privacy and data-retention risk.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

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