Security audit

Qq

Security checks for vulnerabilities and agentic risk

Overview

This QQ skill is a small public-page extraction guide with no code, credentials, persistence, or hidden execution behavior.

Before installing, understand that this skill is intended only for public QQ pages and summaries. Avoid using it for account actions, private messages, authenticated QQ content, or any workflow requiring login or permission bypass; the description should ideally be narrowed to match that boundary.

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

Confidence: 96% confidence
Finding: The description says the skill should be invoked whenever access to or automation of QQ-related content is needed, which is broader than the body of the skill actually allows. That mismatch can cause over-invocation on sensitive or unsupported QQ tasks, increasing the chance an agent routes requests involving login, messaging, or non-public content to this skill despite its later limitations.

Static analysis

No suspicious patterns detected.