ClawHub
Back to skill

Security audit

Tencent Video

Security checks for vulnerabilities and agentic risk

Overview

This skill is a lightweight Tencent Video public-page analysis helper with clear limits against downloads, API calls, bulk scraping, or bypassing platform controls.

Installers should use this only for public Tencent Video page summaries or ranking statistics, keep requests small and user-directed, and avoid using it for downloads, private/account content, reverse engineering, API scraping, or bulk collection.

A.I.G

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

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger description is broad enough to match many Tencent Video-related requests, which can cause the skill to be invoked in situations beyond the author's intended scope. While the skill content itself is relatively constrained and includes compliance-oriented boundaries, over-broad routing can still lead to unnecessary access or automation attempts on third-party content and increase the chance of misapplication.

Content

No source excerpt is available for this finding.