Peekaboo
Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
No outside reports on file
Peekaboo gives AI agents your screen visibility—be careful what's on screen, control which apps it can access, and only use trusted AI models for analysis.
Based on public adoption and transparency signals as of Oct 21, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsNo API token requiredLOW
- Package sourceGitHub (openclaw/Peekaboo)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/openclaw/Peekaboo ↗
Everything known
We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.
0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30
Popularity grade: B (from public signals such as stars and downloads, not a code review). Graded 2026-10-21.
Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.
About Peekaboo
Peekaboo is a tool for macOS that lets AI agents take screenshots of apps or your whole screen. It can also answer questions about what's shown in those screenshots by using AI models running locally or online.
Who it’s for
Developers and AI researchers who want to give AI agents the ability to see and understand what's on a Mac screen. Useful for automating tasks that need visual understanding.
Alternatives
- Anthropic's computer use features (built into Claude API for authorized use)
- OpenAI's vision API (cloud-based image analysis, different privacy model)
- Local LLaVA or similar vision models (open-source, runs on your machine)
- Playwright or Puppeteer (browser automation without visual AI component)
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README at https://github.com/openclaw/Peekaboo (opens external site) for installation and configuration instructions specific to your setup.
Why this grade
Signal-based grade (4/7 points): very widely starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 5.4k
- Listing last refreshed
- 2026-10-29
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Risks to watch for
- Screenshot access: The tool can capture everything visible on your screen, including passwords, private messages, and sensitive documents if an AI agent uses it without limits.
- Visual deception: Misleading images, fake dialogs, or altered screenshots could trick the AI into taking wrong actions or revealing information.
- Unvetted AI models: Using untrusted or remote AI models to analyze screenshots could send your visual data to third parties without your knowledge.
- Privilege escalation: An AI agent with screenshot access might see admin panels, system settings, or other privileged information you didn't intend to share.
- No automatic filtering: The tool doesn't automatically hide sensitive data, so you must manually limit what the AI can see.
How to lower the risk
Least-privilege permissions
- Run the AI agent in a sandboxed or restricted environment when possible.
- Limit which applications the tool is allowed to screenshot.
Network isolation
- Use only local AI models, or verify that remote models are trustworthy before sending screenshots.
- Consider running on an air-gapped machine for highly sensitive work.
Monitoring
- Log what screenshots are captured and which AI queries are made.
- Review AI responses to spot unusual requests or data leaks.
Red flags to watch for
- An AI agent asking to take frequent or unexpected screenshots.
- Requests to screenshot system folders, password managers, or banking sites.
- The tool suddenly connecting to unfamiliar network addresses.
Questions
How do I install Peekaboo?
Peekaboo does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/openclaw/Peekaboo.
Are there security reports about Peekaboo?
No reports found for this package in our research (last checked 2026-10-30). Peekaboo currently holds Grade B (Some risk signals) based on public adoption and transparency signals. Key risk areas to watch include screenshot access, visual deception, unvetted ai models.
Is Peekaboo actively maintained?
Peekaboo has 5.4k GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/openclaw/Peekaboo before pinning it in production.
What are alternatives to Peekaboo?
Notable alternatives to Peekaboo include Anthropic's computer use features, OpenAI's vision API, Local LLaVA or similar vision models, Playwright or Puppeteer. You can also compare Peekaboo side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use Peekaboo? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/openclaw-peekaboo)HTML embed:
<a href="https://agentarmorhq.com/skills/openclaw-peekaboo"><img src="https://agentarmorhq.com/api/badge/openclaw-peekaboo" alt="AgentArmorHQ Risk Grade for Peekaboo" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "openclaw-peekaboo"Share with your security lead
Need sign-off to use Peekaboo? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: Peekaboo
- **Listing URL:** https://agentarmorhq.com/skills/openclaw-peekaboo
- **Type:** App connector
- **Risk Grade:** Grade B (Some risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 5.4k GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** GitHub (openclaw/Peekaboo)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/openclaw/Peekaboo
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 21, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Publisher
- openclaw
- Source code
- github.com/openclaw/Peekaboo
- Est. context load
- ~750 tokens / turn (~4 tool schemas, 0.38% of 200k context)
- Popularity
- 5.4k GitHub stars
- Last updated
- 2026-10-29
- Last graded
- 2026-10-21
Community
Discussions for Peekaboo
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude