ClawHub
Back to skill

Security audit

Greip

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Greip lookup connector, with a notable but disclosed installer risk users should handle carefully.

Install only if you are comfortable using OOMOL as the intermediary for Greip lookups. If the oo CLI is not installed, avoid blindly piping the installer into a shell; review OOMOL’s official install guidance and verify the source before running it. Connect only the Greip credentials/scopes needed for lookups.

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
98% confidence
Finding

The skill instructs users to install software via curl ... | bash, which executes a remotely fetched script without prior verification. If the install server, network path, or hosting account is compromised, this becomes an immediate arbitrary code execution path on the user's machine; because it appears in a setup section of an agent skill, users may follow it with elevated trust.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger condition directs the agent to use this skill for "ANY Greip request," which is overly broad and can cause the skill to be invoked outside a narrowly defined, least-privilege context. Even though the listed actions are read-oriented, this wording encourages blanket delegation and could route unexpected or sensitive Greip-related tasks through shell-based connector execution without additional scope checks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.