ClawHub
Back to skill

Security audit

Google BigQuery

Security checks for vulnerabilities and agentic risk

Overview

The skill fits its BigQuery purpose, but its setup path tells the agent to run an external installer script directly on the host.

Install only if you are comfortable using OOMOL as the BigQuery access path. Do not let an agent run the installer automatically; review and install the oo CLI yourself from a trusted source, then use explicit confirmations for any BigQuery write, update, delete, or export 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
  • 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
95% confidence
Finding

The skill instructs the agent to install software via a remote script piped directly into a shell, which executes unverified code from the network without integrity checking or user review. In an agent context, this is especially dangerous because a failure path ('oo: command not found') can lead directly to code execution on the host, enabling supply-chain compromise or arbitrary command execution if the remote endpoint is compromised or tampered with.

Content

Scanner excerpt · SKILL.md (reported line 86)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation guidance is extremely broad and could overlap with many ordinary tasks that merely mention BigQuery, without clarifying boundaries or exclusions. The file does not provide narrower trigger scope or negative examples to distinguish when this skill should or should not be invoked.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.