ClawHub
Back to skill

Security audit

File Reader

Security checks for vulnerabilities and agentic risk

Overview

This is a simple file-reading skill that only cats a user-specified local file, with no network, persistence, credential handling, or hidden behavior found.

Install only if you want a Chinese-documented helper for reading local files. Be mindful that it will display whatever file path is passed to it, so avoid using it on secrets or sensitive configuration unless that is intentional.

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)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The activation description is broad enough to trigger on common requests like reading or viewing files without sufficiently narrowing scope, which can cause the skill to be invoked in contexts the user did not intend. In a file-reading skill, overbroad activation increases the chance of unnecessary access to local content, including sensitive configuration or source files, especially if higher-level routing is permissive.

Natural-Language Policy Violations

Medium
Confidence
83% confidence
Finding
The skill metadata and documentation are entirely in Chinese, which implies a language constraint, but there is no indication that language is user-selectable or that the skill is intended only for a Chinese-speaking context. This can violate language or locale policy when users have not opted into that language.

Static analysis

No suspicious patterns detected.