ClawHub
Back to skill

Security audit

Ai Content Detection

Security checks for vulnerabilities and agentic risk

Overview

This is a single advisory guide for AI-content detection with no code execution, persistence, credential use, or hidden privileged behavior.

Install only if you want a Chinese-language AI-content-detection reference. Treat its scoring and AI-detection heuristics as investigative guidance, not proof of authorship, fraud, or wrongdoing.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill description is extremely broad and includes many generic authenticity-checking scenarios, which can cause the agent to invoke this skill for ordinary requests that only mention AI, detection, reports, or suspicious content. Over-triggering is risky because the skill contains authoritative but error-prone guidance on AI detection, potentially leading to false accusations, misuse of forensic claims, or the application of weak heuristics outside appropriate contexts.

Natural-Language Policy Violations

Medium
Confidence
98% confidence
Finding
The skill content is written entirely in Chinese without offering language negotiation, which can cause the agent to respond in an unexpected language or misunderstand instructions when the user communicates in another language. In a security-sensitive context, this increases the chance of user confusion, misapplied guidance, and incorrect interpretation of nuanced cautions or limitations in the detection workflow.

Static analysis

No suspicious patterns detected.