openclaw-customizer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Data Exposure & Exfiltration] (SAFE): Use of environment variable placeholders for API keys (e.g., ${TELEGRAM_BOT_TOKEN}) follows security best practices.
- [Indirect Prompt Injection] (LOW): The skill identifies an external documentation source (docs.openclaw.ai) for live updates. This represents a potential surface for indirect injection if the source were compromised, though it is the intended use-case for a documentation assistant. 1. Ingestion points: External URLs in SKILL.md. 2. Boundary markers: Not explicitly defined. 3. Capability inventory: Proposes configuration changes and shell commands for the gateway. 4. Sanitization: None performed on external documentation.
- [External Downloads] (SAFE): References community hubs and documentation fetches which are standard for the documented application's ecosystem.
Audit Metadata