ClawHub
Back to skill

Security audit

Clawdbot Filesystem 1.0.2

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed filesystem-management skill with broad local file search/copy examples, but no hidden code, network use, persistence, or deceptive behavior in the inspected package.

Install only if you want an agent to help inspect and manage local files. Keep searches and analysis limited to project or explicitly authorized directories, avoid broad searches over logs, temp folders, home directories, or credential stores, and review copy operations before allowing write access.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The README promotes full-text content search capabilities but does not warn that searching arbitrary files can expose secrets, credentials, tokens, or other sensitive data in command output or downstream logs. In an agent skill context, this is more dangerous because automated agents may run broad searches over repositories or host filesystems and then echo results into chat, telemetry, or other tools.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The system-administration examples instruct use against sensitive directories like /var/log and /tmp without clearly warning about privacy, log sensitivity, or operational impact. In an AI-agent filesystem skill, such examples can normalize scanning system data and increase the chance that an agent accesses confidential logs or transient files and exposes them in outputs.

Static analysis

No suspicious patterns detected.