superpack-snitchSoft blocklist guard for OpenClaw. Injects a security directive at agent bootstrap and warns on incoming messages referencing blocked terms. Blocks clawhub/c...
Install via ClawdBot CLI:
clawdbot install rgr4y/superpack-snitchGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/rgr4y/superpack-snitchAudited Apr 17, 2026 · audit v1.0
Generated Mar 21, 2026
Financial institutions deploy AI agents to handle customer queries and process transactions. This skill prevents agents from accessing unauthorized external tools like clawhub that could compromise sensitive financial data or violate compliance regulations. It adds a security layer by warning agents about blocked tools during their initialization and when processing incoming messages.
Healthcare providers use AI agents to assist with patient inquiries and administrative tasks. This skill blocks tools that might access or transmit protected health information (PHI) without proper safeguards. The soft enforcement warns agents against using non-compliant tools, helping maintain HIPAA compliance and patient privacy.
Enterprises implement AI agents for internal operations like document processing and data analysis. This skill prevents agents from integrating with unauthorized third-party tools that could introduce security vulnerabilities or data leaks. It serves as a first-line defense by injecting security policies at agent startup.
Educational platforms use AI agents to tutor students and manage course content. This skill blocks tools that might expose students to inappropriate external resources or compromise platform integrity. It flags incoming messages containing references to blocked terms, ensuring a safe learning environment.
E-commerce companies deploy AI agents to handle customer support and order management. This skill prevents agents from using external tools that could access customer payment information or disrupt transaction processes. The blocklist customization allows tailoring to specific e-commerce security needs.
Offer this skill as part of a monthly subscription service for AI agent security. Customers pay for ongoing updates, blocklist management, and support. Revenue comes from tiered pricing based on the number of agents protected and the level of customization required.
License the skill and its plugin version to large organizations for a one-time or annual fee. Include premium features like custom blocklist development, integration support, and priority alerts. This model targets businesses with strict compliance needs and dedicated security budgets.
Provide the basic skill for free to attract users, then monetize the advanced plugin version. The plugin offers hard enforcement, Telegram alerts, and additional security layers. Upsell free users to the paid plugin for enhanced protection and real-time monitoring capabilities.
💬 Integration Tip
Start by setting the SNITCH_BLOCKLIST environment variable with your specific blocked terms, then test with simple agent interactions to ensure warnings appear as expected before scaling deployment.
Scored Jun 19, 2026
Use the ClawdHub CLI to search, install, update, and publish agent skills from clawdhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawdhub CLI.
Mission control dashboard for OpenClaw - real-time session monitoring, LLM usage tracking, cost intelligence, and system vitals. View all your AI agents in o...
Transcribe YouTube videos to text by extracting captions and subtitles directly from the video URL using yt-dlp without audio processing.
Manage a self-hosted Trello-like board via `wekancli`. Create, move and archive cards, lists and boards on a WeKan server. Use when user asks about task boar...
Proactive security monitoring, threat scanning, and auto-remediation for OpenClaw deployments
Create or improve SOUL.md files for OpenClaw agents through guided conversation. Use when designing agent personality, crafting a soul, or saying "help me create a soul". Supports self-improvement.