Outlit Cli

ReviewAudited by ClawScan on May 10, 2026.

Overview

This is mostly a coherent Outlit CLI reference, but it deserves review because it can access customer data and includes a no-confirm command to configure all detected AI agents.

Install only if you intend to use Outlit CLI with your Outlit account. Be careful with API keys and customer-data outputs, and avoid the broad `outlit setup --yes` path unless you understand exactly which AI-agent configurations it will change.

Findings (4)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

ConcernMedium Confidence
ASI02: Tool Misuse and Exploitation
What this means

Running this command could change multiple AI-agent environments at once without a per-agent review prompt.

Why it was flagged

The skill documents a no-confirm setup command that can configure every detected AI agent. That is purpose-related, but it is broad and lacks details about which agents/files are changed, what permissions are needed, or how to review and undo the changes.

Skill content
`outlit setup` | Auto-detect and configure AI agents ... **Setup all detected agents at once:** `outlit setup --yes`
Recommendation

Prefer configuring a specific agent, such as `outlit setup openclaw`, and avoid `--yes` unless you have reviewed what the CLI will modify and know how to roll it back.

What this means

Anyone or any process with access to the stored key or environment variable may be able to query the associated Outlit account.

Why it was flagged

The skill uses an Outlit API key and can store it locally. This is expected for the Outlit CLI, but the registry metadata does not declare a primary credential or env vars.

Skill content
`outlit auth login` | Store API key ... Credential priority: `--api-key` flag, `OUTLIT_API_KEY` env var, `~/.config/outlit/credentials.json`
Recommendation

Use least-privileged API keys if available, avoid putting real keys in shared shell history or logs, and run `outlit auth logout` when the integration is no longer needed.

What this means

Sensitive customer or business information could be displayed in chat, terminal logs, shell history, or copied into later agent context.

Why it was flagged

The documented commands can retrieve customer, user, revenue, event, and behavioral context into the terminal and potentially into the agent conversation.

Skill content
`outlit customers get <id|domain>` ... `--include users,revenue,recentTimeline,behaviorMetrics`; `events` | All tracked events; `outlit search '<query>'` | Natural language search across customer context
Recommendation

Query only the customers and fields needed, avoid pasting sensitive outputs into unrelated chats, and treat CLI results as confidential business data.

What this means

The security of the installed CLI depends on the npm package and its dependencies, which were not reviewed here.

Why it was flagged

The reviewed skill contains only instructions and tells users to install a global npm CLI package whose source code is not included in the artifacts.

Skill content
Customer intelligence from the terminal. Install: `npm i -g @outlit/cli`
Recommendation

Install only from the expected npm package, verify the publisher/version where possible, and consider pinning a known-good version in managed environments.