ClawHub
Back to skill

Security audit

Guru

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Guru read/search connector that uses OOMOL's oo CLI and does not show hidden, destructive, or unrelated behavior.

Install this if you want Codex to search and read Guru content through your connected OOMOL account. Be aware that Guru results may include private workspace knowledge visible to that account, and only complete the oo CLI/OOMOL connection setup if you trust OOMOL with that integration.

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
92% confidence
Finding
The manifest description says to use this skill for "ANY Guru request" and "instead of calling the API directly," which is an overly broad activation trigger. This can cause the agent to invoke the skill in situations where Guru is only tangentially mentioned, increasing the chance of unnecessary data access or unintended retrieval of sensitive workspace content through the connected account.

Static analysis

No suspicious patterns detected.