ClawHub

Notifications Engine

v1.0.0

Multi-channel notification delivery with customizable templates, email and SMS sending, and full delivery logging — built for AI agents.

⭐ 0· 39·0 current·0 all-time
by@cameron48
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
medium confidence
✓
Purpose & Capability
Name, description, and the SKILL.md endpoints align: the skill describes a notification API (templates, send, logs) and lists corresponding HTTP endpoints. It does not request unrelated binaries or environment variables.
ℹ
Instruction Scope
SKILL.md instructs the agent to use an external gateway (gateway.mcfagentic.com) and lists endpoints/prices. It does not ask the agent to read local files or credentials, but it is terse — missing payload schema, headers, expected responses, and privacy guidance. The agent will transmit notification content (potentially sensitive) to an external service.
✓
Install Mechanism
Instruction-only skill with no install spec or downloadable artifacts, so nothing is written to disk by an installer step.
✓
Credentials
No environment variables, credentials, or config paths are requested. The only externally required action is payment via the stated x402 (USDC on Base) mechanism, which is handled outside the skill metadata.
✓
Persistence & Privilege
always is false and the skill does not request persistent system-wide changes. The default ability for the agent to invoke the skill autonomously remains (platform default) but is not elevated by the skill itself.
Assessment
This skill appears coherent for sending notifications, but take these precautions before installing: verify who runs gateway.mcfagentic.com (request publisher/homepage and documentation), confirm pricing and how payments (USDC on Base L2) are initiated and billed, and ensure you are comfortable that notification content (emails/SMS) will be sent to that external service (avoid sending sensitive personal data until you trust the provider). Because the skill will allow the agent to call an external API, review and restrict the agent's autonomy/permissions if you don't want it sending messages without approval. If you plan to rely on this in production, ask the publisher for API request/response formats, privacy policy, and an alternative billing/auth scheme (API key) you can audit.

Like a lobster shell, security has layers — review code before you run it.

latestvk9732rq49n10dz1cmv8kdv5mvs843p01

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments