ClawHub
Back to skill

Security audit

go-weave

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only helper for using an unofficial Go client with W&B Weave, and its credential and network behavior is disclosed and purpose-aligned.

Before installing, treat github.com/psyb0t/go-weave as an unofficial third-party Go dependency, keep WANDB_API_KEY out of source control and logs, and only use destructive Weave delete or purge methods when you intentionally asked for that action.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

This markdown file instructs users to provide a W&B username and API key via environment variables, which involves sensitive credential handling. The setup guide does not include any warning about protecting these values, avoiding accidental exposure, or the fact that subsequent client requests will use them for authentication.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.