Prompt Guard owner avatar

Prompt Guard

Alert level: High

Advanced prompt injection defense system for Clawdbot with HiveFence network integration. Protects against direct/indirect injection attacks in group chats with multi-language detection (EN/KO/JA/ZH), severity scoring, automatic logging, and configurable security policies. Connects to the distributed HiveFence threat intelligence network for collective defense.

Locality:Hybrid
Data access:Sensitive
Actions:Write
Installs 4Downloads 2918Stars 18Updated 229h ago

Why this rating

Deterministic checks triggered by the tool capabilities and evidence.

  • Locality: Hybrid

    Uses local detection logic plus optional HiveFence network integration via remote API URL.

  • Data access: Sensitive

    Inspects conversation content for secrets, credentials, and high-risk prompt patterns.

  • Action surface: Write

    Supports threat reporting/voting and policy-driven logging/blocking actions.

Best practices

Follow these steps to reduce risk when using this skill.

  • Treat flagged content as potentially malicious and require review before any privileged action.
  • Avoid sending full sensitive payloads to external reporting channels when pattern-only reports are sufficient.
  • Tune severity policies with audit logs so false positives do not silently block legitimate workflows.

Evidence links

Public sources backing the indicator assignments.

Always be careful when navigating away from the website.

Max-risk rule

If any capability reaches a higher level, the entire indicator level bumps up to keep ratings deterministic and easy to scan.