Skip to main content
The threat model is a living document. Contributions are welcome from anyone; you do not need security or MITRE ATLAS background.
This is for adding to the threat model, not reporting live vulnerabilities. If you found an exploitable vulnerability, follow the responsible-disclosure instructions on the Trust page instead.

​
Ways to contribute

Add a threat. Open an issue on openclaw/trust describing the attack scenario in your own words. Helpful but not required:
  • The attack scenario and how it could be exploited.
  • Which components are affected (CLI, gateway, channels, ClawHub, MCP servers, etc.).
  • Your estimate of severity (low / medium / high / critical).
  • Links to related research, CVEs, or real-world examples.
Maintainers assign the ATLAS mapping, threat ID, and risk level during review. Suggest a mitigation. Open an issue or PR referencing the threat. Be specific and actionable: “per-sender rate limiting of 10 messages/minute at the gateway” is more useful than “implement rate limiting.” Propose an attack chain. Attack chains show how multiple threats combine into a realistic scenario. Describe the steps and how an attacker would chain them; a short narrative beats a formal template. Fix or improve existing content. Typos, clarifications, outdated info, better examples: PRs welcome, no issue needed.

​
Framework reference

Threats are mapped to MITRE ATLAS (Adversarial Threat Landscape for AI Systems), a framework for AI/ML-specific threats like prompt injection, tool misuse, and agent exploitation. You do not need to know ATLAS to contribute; maintainers map submissions during review. Threat IDs. Each threat gets an ID like T-EXEC-003, assigned by maintainers during review.
CodeCategory
RECONReconnaissance - information gathering
ACCESSInitial access - gaining entry
EXECExecution - running malicious actions
PERSISTPersistence - maintaining access
EVADEDefense evasion - avoiding detection
DISCDiscovery - learning about the environment
EXFILExfiltration - stealing data
IMPACTImpact - damage or disruption
Risk levels. If you are unsure about the level, just describe the impact; maintainers assess it.
LevelMeaning
CriticalFull system compromise, or high likelihood + critical impact
HighSignificant damage likely, or medium likelihood + critical impact
MediumModerate risk, or low likelihood + high impact
LowUnlikely and limited impact

​
Review process

  1. Triage - new submissions are reviewed within 48 hours.
  2. Assessment - maintainers verify feasibility, assign ATLAS mapping and threat ID, validate risk level.
  3. Documentation - formatting and completeness pass.
  4. Merge - added to the threat model and visualization.

​
Resources

​
Contact

  • Security vulnerabilities: Trust page for reporting instructions, or security@openclaw.ai.
  • Threat model questions: open an issue on openclaw/trust.
  • General chat: Discord #security channel.

​
Recognition

Contributors to the threat model are recognized in the threat model acknowledgments, release notes, and the OpenClaw security hall of fame for significant contributions.