ClawHub
Back to skill

Security audit

Filesystem

Security checks for vulnerabilities and agentic risk

Overview

This filesystem skill is broad but its local file listing, searching, copying, and analysis behavior is disclosed and aligned with its stated purpose.

Install only if you want an agent to perform local filesystem operations. Review paths and use dry-run for copy operations, since broad file access can expose or modify local project data if invoked on the wrong directory.

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 (1)

Vague Triggers

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

This manifest describes the skill only as "Advanced filesystem operations" with broad capabilities like listing, searching, batch processing, and analysis, but does not define concrete trigger phrases, scope limits, or exclusion conditions. In a skill-routing context, such a generic description can overlap with many common file-related requests and increase the chance of unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.