ClawHub
Back to skill

Security audit

RedHat File Operations

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed file-operations helper, but its malformed trigger metadata makes activation scope unclear for a skill that can change or delete files.

Review the trigger metadata before installing. The skill's behavior is transparent and safety-oriented, but because it can modify or delete files, it should only run with explicit, narrow activation rules and workspace path limits.

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

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger field is effectively unspecified and appears to contain a serialized type placeholder ('System.Object[]') rather than concrete trigger definitions. This can cause the skill to activate unpredictably, be matched too broadly, or bypass intended invocation constraints, which is risky for a file-operations skill that can modify filesystem state.

Content

No source excerpt is available for this finding.