ClawHub
Back to skill

Security audit

Eraser

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for managing Eraser through OOMOL, but its fallback setup tells an agent to run remote install scripts directly, which is high-impact local execution without verification.

Install only if you are comfortable using OOMOL as an intermediary for your Eraser account. Avoid letting an agent run the pasted curl-to-bash or iex installer automatically; install the oo CLI through verified official steps, then review and approve any write or destructive Eraser action before it runs.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The skill instructs the agent to install software via a remote script piped directly into bash, which executes network-fetched code without prior verification. If the install endpoint, transport, or upstream distribution is compromised, this can lead to arbitrary code execution on the host running the skill.

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill description says to use this skill for ANY Eraser request, which is overly broad and can cause the agent to invoke it whenever Eraser is merely mentioned rather than when its use is clearly intended. In a skill that supports reads, writes, and destructive operations, this ambiguity increases the chance of unintended tool execution and unnecessary exposure to state-changing capabilities.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.