ClawHub
Back to skill

Security audit

xhs-report-generate

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed XiaoHongshu public-data research tool that uses a third-party API and saves successful results locally, with no evidence of hidden account access, posting, deletion, or exfiltration beyond its stated data service.

Install only if you are comfortable sending XiaoHongshu keywords or URLs to the guaikei.com API using a GUAIKEI_API_TOKEN. Successful results are saved locally under logs, so review and delete those files if the searches, target accounts, comments, or fetched public data are sensitive.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Context-Inappropriate Capability

Medium
Confidence
83% confidence
Finding
The CLI writes full search output to a local file whose name includes the user keyword. This creates an undeclared persistence channel for potentially sensitive research terms and result data, which can expose user activity to other local users, backups, or later processes, especially on shared systems. The risk is increased because the manifest emphasizes search/view/reporting behavior but does not disclose local retention.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The README states that all task results are automatically saved to the `logs/` directory, but it does not clearly warn users that searched keywords, queried profile/note URLs, comments, and fetched platform data will be persisted locally. In this skill’s context, those artifacts can reveal marketing plans, competitor targets, research subjects, or scraped third-party content, creating confidentiality and retention risks if the host machine is shared, backed up, or later compromised.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The code sends the API token and target URL in GET query parameters when retrieving task results. Query parameters are commonly exposed in logs, browser history, reverse proxies, monitoring systems, and referrer data, so placing credentials there increases the chance of accidental disclosure even if HTTPS is used.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The CLI persists fetched note details and comments to a local JSON file automatically, which can retain potentially sensitive or regulated content longer than the user expects. On shared machines, CI runners, or agent environments, these files may be accessible to other users, included in backups, or unintentionally committed to source control, increasing data exposure risk.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The CLI persists fetched Xiaohongshu results to a local JSON file automatically after execution, but the visible user messaging does not clearly disclose that potentially sensitive scraped data will be stored on disk. In shared environments, CI runners, or multi-user systems, this can create unintended data retention and local exposure risks, especially when the results may include public-profile-derived content, metadata, and comments aggregated at scale.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.