Security audit

Kuaishou Dashi

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Kuaishou public-data collection tool that uses a third-party API and saves local result logs, with no evidence of account posting, hidden execution, or persistence beyond those logs.

Install only if you are comfortable using a third-party guaikei.com API token and sending Kuaishou search terms or URLs to that service. Treat saved logs as retained local copies of the fetched public data, especially on shared machines, and delete the logs directory when results should not remain on disk.

A.I.G

By Tencent

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

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
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (4)

Context-Inappropriate Capability

Medium

Confidence: 88% confidence
Finding: The package markets itself as a data-analysis and monitoring tool, but its exposed npm scripts include posting and commenting actions. This mismatch can mislead users into granting trust or running automation that performs external account actions, increasing the risk of spam, unauthorized engagement, or policy-violating behavior.

Description-Behavior Mismatch

Medium

Confidence: 91% confidence
Finding: The declared description emphasizes analytics, market research, and growth insights, while the package entrypoints suggest it can also publish content and submit comments. In a skill ecosystem, that discrepancy is security-relevant because users and reviewers may underestimate the operational scope and approve a package that can take active actions on third-party platforms.

Missing User Warnings

Medium

Confidence: 75% confidence
Finding: The script persists fetched post results to a local JSON file without explicit notice, consent, or an opt-out mechanism. If the fetched data contains sensitive account information or is run in shared environments, this can leave recoverable artifacts on disk and unintentionally expose data to other local users, backup systems, or later processes.

Missing User Warnings

Low

Confidence: 86% confidence
Finding: The CLI writes the full search output to a local JSON file named with the keyword and parameters, but this file behavior is not clearly surfaced to the user at the time of execution. Because search results and query terms may contain sensitive or proprietary information, silent persistence can create unintended local data exposure to other users, backup systems, or later forensic recovery.

VirusTotal

56/56 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