ClawHub
Back to skill

Security audit

Okf Knowledge Format

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for managing OKF knowledge bundles, but it directs installation of an unpinned CLI directly from GitHub.

Review and install the OKF CLI manually only if you trust the source. Prefer a pinned, integrity-verifiable release or a vetted package-index install when available. The skill's OKF file-management instructions themselves are otherwise narrowly scoped.

SkillSpector

Vulnerability Patterns
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • 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)

YARA rule 'agent_skill_remote_bootstrap_execution': Remote script or code download followed by execution/bootstrap installation [agent_skills]

High
Category
YARA Match
Content
- OKF Spec: https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md
- okf-toolkit: https://github.com/akdira/okf-toolkit
- Project home: [akdira](https://www.akdira.id)
- Install: `pip install git+https://github.com/akdira/okf-toolkit.git`

---
Confidence
91% confidence
Finding
The skill instructs users/agents to install and run code directly from a GitHub repository via `pip install git+https://...`, which bypasses normal package registry trust controls and can fetch mutable remote code at install time. In an agent skill context, this is especially dangerous because an automated agent may follow the instruction and execute unreviewed setup code from an external source, enabling supply-chain compromise or arbitrary code execution if the repository is malicious or later altered.

Static analysis

No suspicious patterns detected.