ClawHub
Back to skill

Security audit

Weights & Biases

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Weights & Biases connector, but it needs review because it is broadly invoked and one action that writes to W&B is not clearly labeled as a write action.

Review before installing. This does not show malicious behavior, but users should confirm exactly what W&B project/entity an action will access and require explicit approval for any action that creates reports, logs runs, or otherwise changes W&B state, including `log_analysis`.

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
Confidence
89% confidence
Finding
The trigger text is extremely broad: it instructs use of this skill for ANY Weights & Biases request and instead of calling the API directly. That can cause unintended invocation on casual mentions of W&B, routing unrelated or insufficiently scoped tasks through a powerful connector that can both read and write account data, increasing the chance of over-collection, accidental state changes, or misuse of connected credentials.

Static analysis

No suspicious patterns detected.