ClawHub
Back to skill

Security audit

Weights & Biases

Security checks for vulnerabilities and agentic risk

Overview

This skill’s W&B connector behavior is mostly clear, but its first-time setup tells the agent to install a CLI by executing a remote script without verification or explicit user approval.

Review this skill before installing. It may be reasonable if you already trust OOMOL and have the oo CLI installed, but do not let an agent run the remote installer automatically; install the CLI through a trusted, verified method and confirm any W&B write action payload before execution.

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 by piping a remote script directly into a shell (curl ... | bash). This is dangerous because it executes unverified code fetched at runtime from an external server, creating a supply-chain and remote code execution risk if the endpoint, transport, or distribution pipeline is compromised.

Content

Scanner excerpt · SKILL.md (reported line 76)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description says to use this skill for ANY Weights & Biases request, which can cause overly aggressive routing of user requests into a tool-capable skill without clear scope limits or safety gating. In practice, this increases the chance that ambiguous W&B-related requests, including sensitive or state-changing ones, are handled by the skill by default rather than by a narrower, least-privilege path.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.