ClawHub
Back to skill

Security audit

Kuai Shou Ai Feed

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Kuaishou public-data collection CLI that uses a third-party API token and saves results locally, with privacy considerations users should understand.

Install only if you are comfortable sending Kuaishou keywords or URLs to the GUAIKEI third-party API and storing returned public-data results under the skill's local logs directory. Avoid using it for private, login-only, or sensitive investigations, and delete local logs when they are no longer needed.

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 (5)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The script writes the full result payload to a local file named from user-derived data without any explicit notice, consent flow, or data-minimization step. Because the output includes request details and fetched results, this can leave potentially sensitive scraped data on disk unexpectedly, increasing exposure through other local users, backups, or later reuse.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The script sends a user-supplied profile URL together with an API token to remote APIs via createPostTask/getPostTask, but this file gives no explicit disclosure that provided input will be transmitted to an external service. Users may reasonably believe a CLI validator operates locally, so silent transmission of identifiers or profile URLs can create privacy, compliance, and trust issues.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The CLI writes the full search output, including the user's keyword and returned results, to a local JSON file without any explicit consent, disclosure, or opt-in control in this file. Because search queries and results may contain sensitive or proprietary information, silent persistence can create unintended local data exposure through shared machines, backups, log collection, or later compromise of the host.

Ssd 3

Medium
Confidence
88% confidence
Finding
The skill normalizes broad collection of creator/commenter data and emphasizes returning all visible valuable data plus automatic log archiving. Even if the source is described as public, bulk aggregation, retention, and broad return of user-related data can increase privacy risk, create excessive data handling, and enable downstream misuse beyond a user's immediate need.

Ssd 3

Medium
Confidence
91% confidence
Finding
The skill explicitly instructs retrieval of comment content, commenter information, and interaction data, while also acknowledging dependence on a third-party API for data externalization. This creates a meaningful privacy and compliance risk because user-related data is being systematically collected and transmitted to an external service, potentially beyond what is strictly necessary for the requested analysis.

VirusTotal

64/64 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:15