Free AI Safety Workshop — in collaboration with explainx.aiSave your seat
AgentbeamBeta
AI agent vulnerability · OpenClaw

CVE-2026-35655: OpenClaw's Conflicting Tool Identity Hints Bypass Dangerous-Tool Prompting

mediumCVSS 4.0 6.9 · 3.1 5.7GHSA-74wf-h43j-vvmj

Summary ACP permission resolution trusted conflicting tool identity hints from rawInput and metadata, which could suppress dangerous-tool prompting. Affected Packages / Versions - Package: openclaw (npm) - Affected: = 2026.3.22 - Latest released tag checked: v2026.3.23-2 (630f1479c44f78484dfa21bb407cbe6f171dac87) - Latest published npm version checked: 2026.3.23-2 Fix Commit(s) -…

Published Mar 26, 2026 · Updated Apr 10, 2026

Affected packages

openclaw

Ecosystem
npm
Affected
< 2026.3.22
Fixed in
2026.3.22
Check
npm ls openclaw

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

Summary

ACP permission resolution trusted conflicting tool identity hints from rawInput and metadata, which could suppress dangerous-tool prompting.

Affected Packages / Versions

  • Package: openclaw (npm)
  • Affected: < 2026.3.22
  • Fixed: >= 2026.3.22
  • Latest released tag checked: v2026.3.23-2 (630f1479c44f78484dfa21bb407cbe6f171dac87)
  • Latest published npm version checked: 2026.3.23-2

Fix Commit(s)

  • e4c61723cd2d530680cc61789311d464ab8cdf60

Release Status

The fix shipped in v2026.3.22 and remains present in v2026.3.23 and v2026.3.23-2.

Code-Level Confirmation

  • src/acp/client.ts now fails closed when meta, rawInput, and title tool identities conflict instead of trusting spoofable raw input.
  • src/acp/client.test.ts ships regressions for conflicting tool identity hints and dangerous-tool prompting.

OpenClaw thanks @zpbrent for reporting.

Credited to zpbrent.

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More OpenClaw vulnerabilities

All OpenClaw entries