obot
Complete AI Governance Platform from Obot AI
3 incidents on file
This tool touches core AI execution and security policies, so misconfigurations or supply-chain risks could undermine your entire AI governance strategy.
Based on public adoption and transparency signals as of Oct 29, 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 (obot-platform/obot)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/obot-platform/obot ↗
Everything known
2 high incidents and 1 medium incident on record. The newest is from 2026-09-18. Every report lists a fix. Use 0.23.0 or later to get them all.
3 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30
Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-29.
Showing all 3Showing 3 incidents of 3
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 Obot
Obot is a platform designed to help organizations manage and govern AI systems. It appears to provide tools for controlling how AI agents behave, setting policies, and monitoring their activities.
Who it’s for
Organizations that deploy AI agents internally and want centralized control over security, permissions, and compliance. Teams that need to manage multiple AI systems across their company.
Alternatives
- Anthropic Claude Governance API (if using Claude models internally for control and monitoring). - LiteLLM Proxy (for centralized access control and logging of AI model calls). - OpenAI API platform controls (built-in governance for OpenAI deployments). - Custom audit layer (in-house logging and policy enforcement tailored to your specific AI stack).
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README at https://github.com/obot-platform/obot (opens external site) for installation and configuration instructions specific to your environment.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 1.1k
- 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
- Broad system access: An AI governance tool typically needs access to logs, configuration systems, and agent communications—giving it visibility into sensitive business processes. - Policy bypasses: If governance rules are misconfigured or incomplete, AI agents could circumvent intended restrictions. - Credential exposure in logs: Monitoring agent activity might inadvertently capture API keys, tokens, or secrets passed through messages. - Privilege escalation: The platform itself needs high permissions to enforce policies, so a compromise could affect all connected AI systems. - Misleading governance reports: Attackers could craft inputs that make agents appear compliant when they are not, or hide unauthorized actions in logs.
How to lower the risk
Least-privilege permissions
- Grant the governance platform only permissions it absolutely needs to monitor and control agents.
- Separate read-only auditing roles from policy-enforcement roles.
Network isolation
- Run the platform in a restricted network segment with limited outbound access.
- Use a private, authenticated instance rather than a public-facing deployment.
Monitoring
- Log all policy changes and governance decisions for audit trails.
- Set up alerts for unusual patterns in agent behavior or policy modifications.
Red flags to watch for
- Agents consistently bypassing or contradicting configured policies.
- Unexplained gaps in activity logs or monitoring data.
- Performance degradation that could mask unauthorized agent actions.
Questions
How do I install Obot?
Obot does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/obot-platform/obot.
Are there security reports about Obot?
3 reports were found for this package in our research. Titles and dates (AgentArmorHQ incident library) are listed in the Reports section above. Obot currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include broad system access.
Is Obot actively maintained?
Obot has 1.1k GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/obot-platform/obot before pinning it in production.
What are alternatives to Obot?
Notable alternatives to Obot include Anthropic Claude Governance API. You can also compare Obot side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use Obot? 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/obot-platform-obot)HTML embed:
<a href="https://agentarmorhq.com/skills/obot-platform-obot"><img src="https://agentarmorhq.com/api/badge/obot-platform-obot" alt="AgentArmorHQ Risk Grade for Obot" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "obot-platform-obot"Share with your security lead
Need sign-off to use obot? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: obot
- **Listing URL:** https://agentarmorhq.com/skills/obot-platform-obot
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 3
- **Public Adoption:** 1.1k 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 (obot-platform/obot)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/obot-platform/obot
- **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 29, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Publisher
- obot-platform
- Source code
- github.com/obot-platform/obot
- Est. context load
- ~700 tokens / turn (~4 tool schemas, 0.35% of 200k context)
- Popularity
- 1.1k GitHub stars
- Last updated
- 2026-10-29
- Last graded
- 2026-10-29
Community
Discussions for Obot
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