ClawHub
Back to skill

Security audit

AI Sting (AI 刺客)

Security checks for vulnerabilities and agentic risk

Overview

This red-team skill is transparent about generating copy-paste AI attack prompts, but it lacks clear authorization limits and should be reviewed before use.

Install only if you intend to use it for authorized AI security testing. Before relying on it, add or enforce a rule that attack prompts are generated only for systems you own or have permission to test, and avoid using its outputs against third-party assistants or production systems without approval.

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 (3)

Ssd 2

High
Confidence
98% confidence
Finding
This instruction explicitly directs the model to generate tailored attack prompts against a target agent, including practical offensive content a user can immediately use. Even though it is framed as testing, the skill does not require proof of authorization or enforce strong defensive boundaries, so it materially lowers the barrier to conducting prompt injection, privilege impersonation, and bypass attacks.

Ssd 2

High
Confidence
99% confidence
Finding
The weaponization section operationalizes abuse by requiring three copy-paste malicious prompts spanning jailbreak, social engineering impersonation, and encoded or fictional bypass methods. The surrounding skill context makes this more dangerous, not less, because the entire role is optimized to produce effective offensive payloads tailored to specific business domains, enabling real-world misuse against deployed assistants.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The activation text is broad enough to trigger on many general security or prompt-related requests, which increases the chance this skill is invoked outside a tightly scoped defensive assessment workflow. In this case that matters because the skill also contains explicit instructions to generate copyable attack prompts, so over-broad routing raises the probability of unsafe misuse.

Static analysis

No suspicious patterns detected.