ClawHub
Back to skill

Security audit

爱奇艺

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed iQiyi search, recommendation, and playback helper with network and deeplink behavior that fits its stated purpose.

Before installing, be aware that the skill can send iQiyi search or recommendation queries to iQiyi’s mesh API and can generate qips deeplinks that open or control the iQiyi client when you ask for playback. Do not provide an Authorization header unless you intend it to be sent to the iQiyi API for history or favorites behavior.

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
Confidence
92% confidence
Finding
The skill enables implicit invocation without any documented trigger constraints or exclusions, which can cause the agent to auto-select this skill in broader conversational contexts than intended. Because this skill can search, recommend, and initiate playback behavior, unintended invocation may expose users to unrequested external content flows or cause the model to rely on this skill when the user did not explicitly ask for iQiyi actions.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
scripts/iqiyi-skill-catalog.mjs:520

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
scripts/iqiyi-skill-catalog.test.mjs:175