ClawHub
Back to skill

Security audit

Ram Review

Security checks for vulnerabilities and agentic risk

Overview

This is a small Chinese-language persona review skill with no code, install scripts, persistence, credential access, or data exfiltration behavior.

Install this if you want a Chinese persona that critiques prior assistant work in character. Be aware that broad phrases like asking what Ram thinks may activate the persona, so clearer trigger wording would reduce accidental invocation in multi-skill setups.

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 (2)

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The file presents the skill entirely in Chinese and specifies a fixed Chinese persona and response style, but it does not indicate that language choice is optional or user-selectable. Under the policy, imposing a specific language or locale without opt-in is a natural-language policy concern unless the constraint is clearly justified.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger phrases are broad and conversational, which increases the chance the skill is invoked unintentionally during ordinary discussion rather than through an explicit command. In a multi-skill or agent setting, this can cause incorrect routing, confusing behavior, or unauthorized persona switching, even though the skill itself is not performing a sensitive action.

Static analysis

No suspicious patterns detected.