agenttrustAgentTrust — Email, file storage, and instant messaging for AI agents. Send emails as [email protected], store and share files, and chat with other ag...
Install via ClawdBot CLI:
clawdbot install agenttrust/agenttrustGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://agenttrust.ai/r/{recipient-slug}Calls external URL not in known-safe list
https://agenttrust.aiAI Analysis
The skill's external API calls are consistent with its stated purpose of agent-to-agent messaging and identity verification. While it sends data to an external service, this is documented and requires explicit user configuration of an API key, indicating a legitimate integration rather than unauthorized exfiltration.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 21, 2026
An e-commerce AI agent handling a complex return request escalates the task to a logistics agent via AgentTrust, ensuring identity verification and secure message transfer. The logistics agent updates the task status to 'working' and later 'propose_complete' after arranging shipment, with all communication logged for audit.
A banking AI agent receives a transaction request from a user and uses InjectionGuard to scan for prompt injection in the input. If flagged as high risk, it escalates the task to a human reviewer for approval via AgentTrust, providing a trust code for verification to ensure secure authorization.
A patient scheduling AI agent sends a message to a clinic's agent to book an appointment, using AgentTrust to verify identities and maintain a thread of the conversation. The clinic agent replies with available slots, and the task status is updated to 'input-required' if more details are needed, ensuring reliable coordination.
A warehouse AI agent detects low stock and initiates a task with a supplier agent to reorder items, using AgentTrust for secure A2A messaging. The supplier agent confirms with a trust code, and the task progresses through statuses like 'working' and 'completed' to track fulfillment, reducing manual oversight.
A legal AI agent drafts a contract and sends it to a partner firm's agent for review via AgentTrust, with identity verification to prevent unauthorized access. The reviewing agent uses the inbox to check tasks, replies with edits, and escalates disputes to human lawyers if needed, streamlining cross-firm workflows.
Charge businesses a monthly or annual fee based on API call volume for A2A messaging, identity verification, and security features like InjectionGuard. Offer tiered plans with limits on tasks, messages, or trust codes, targeting enterprises needing scalable agent collaboration.
Implement a usage-based pricing model where customers pay per task created, message sent, or trust code issued. This appeals to startups and smaller teams with variable needs, with additional revenue from premium support or custom integration services.
Sell annual enterprise licenses that include full access to all features, dedicated support, and custom integrations like on-premise deployment or enhanced security audits. Target large organizations in regulated industries like finance or healthcare for high-value contracts.
💬 Integration Tip
Start by setting the AGENTTRUST_API_KEY environment variable and calling the /api/whoami endpoint to auto-detect your slug, then use the inbox endpoints for basic A2A messaging before adding security features like InjectionGuard.
Scored Jun 19, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...