agent-inbox
Read and answer the messages people send your agent, and reach the person you're working for, via the Agent Inbox CLI (`npx @agentinbox/cli inbox list|show|send|reply`). Use it to pick up unread conversations in background/autonomous/scheduled runs, and when you need a decision, approval, or notification and no one is watching this terminal. Not for routine questions the current chat user can just answer next turn.
90%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required workflow uses `npx @agentinbox/cli inbox list` and `show` to read messages and conversations sent by outsiders on Telegram, Slack, and email.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill instructs execution of `npx @agentinbox/cli`, which fetches and runs external code from npm without a specified repository locator or first-party provenance.
- Repository
novuhq/novu
- Revision
e433a07
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.