Security audit
Security checks for vulnerabilities and agentic risk
This appears to be a legitimate disposable email integration, but it needs Review because shared agents can read full inbox contents such as verification links and OTPs.
Install only if you are comfortable using AgentPMT-hosted disposable inboxes where other agents on the same budget may be able to inspect messages. Do not use it for personal, financial, production, or high-value accounts; isolate agent groups or budgets for private workflows, and prefer explicit temporary-inbox requests over generic email tasks.
The skill explicitly states that disposable inboxes are shared across agents on the same budget and that any one of them can check the inbox, yet it lacks a prominent user-facing warning and consent requirement. This creates a real privacy and confidentiality risk: verification links, OTPs, and other message contents may be visible to unrelated agents operating under the same budget boundary.
The top-level description uses broad discovery language around signups, registration, verification links, and generic email actions, which increases the chance of ambiguous matching. In this context, accidental activation is more dangerous because the tool interacts with a third-party service and can receive/read full email content shared across agents on the same budget.
The activation keywords include very broad generic terms such as check, email, and create, which can cause accidental invocation in unrelated workflows. Because this skill can create inboxes and read full message contents, unintended activation could expose sensitive verification emails or route data to an external service without clear user intent.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- What AgentPMT is: ../what-is-agentpmt (ClawHub: `what-is-agentpmt`, page: https://clawhub.ai/agentpmt/what-is-agentpmt; skills.sh: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`)
- AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup (ClawHub: `agentpmt-account-mcp-rest-api-setup`, page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup; skills.sh: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`)
- Marketplace product: https://www.agentpmt.com/marketplace/disposable-email-address
- AgentPMT main MCP server: https://api.agentpmt.com/mcp/
- AgentPMT REST invoke endpoint: https://api.agentpmt.com/products/purchase
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- What AgentPMT is: ../what-is-agentpmt (ClawHub: `what-is-agentpmt`, page: https://clawhub.ai/agentpmt/what-is-agentpmt; skills.sh: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`)
- AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup (ClawHub: `agentpmt-account-mcp-rest-api-setup`, page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup; skills.sh: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`)
- Marketplace product: https://www.agentpmt.com/marketplace/disposable-email-address
- AgentPMT main MCP server: https://api.agentpmt.com/mcp/
- AgentPMT REST invoke endpoint: https://api.agentpmt.com/products/purchase
The skill description states that the check action retrieves full message content including sender, subject, and body, which is privacy-sensitive user data. In this markdown file, there is no accompanying warning or disclosure about handling potentially sensitive email contents.
No suspicious patterns detected.