GHSA-w5c7-9qqw-6645: Openclaw OpenClaw Inter-session Prompts Could Be Vulnerability

HIGH
CWE-345
Published
Advisory Summary

GHSA-w5c7-9qqw-6645 is a HIGH openclaw inter-session prompts could be vulnerability (CWE-345: Insufficient Verification of Data Authenticity) affecting Openclaw libraries in the npm ecosystem. The issue involves openclaw inter-session prompts could be treated as direct user instructions. Remediation is available by upgrading affected packages to version 2026.2.13.

GHSA-w5c7-9qqw-6645 at a Glance

CVE Identifier N/A
GHSA Identifier GHSA-w5c7-9qqw-6645
Severity HIGH
CVSS v3.1 Base Score N/A
CWE Classification CWE-345: Insufficient Verification of Data Authenticity
Affected Product Openclaw
Package Ecosystem npm
Published Date
Last Updated

How to Fix GHSA-w5c7-9qqw-6645

To remediate this vulnerability, upgrade all affected Openclaw dependencies to a patched release. Both direct and transitive dependencies should be checked, as frameworks or security libraries may pull in vulnerable versions transitively.

openclaw fixed: 2026.2.13
npm install openclaw@2026.2.13
Verify Direct and Transitive Dependencies

Run the following command in your project directory to verify that all resolved dependencies use the patched release:

npm ls openclaw

How to Check if You Are Affected

To determine whether your Node.js application is affected by GHSA-w5c7-9qqw-6645, inspect your project dependencies using npm:

npm ls openclaw

Analyze the terminal output to locate any version of Openclaw in your dependency tree. If any resolved version matches the vulnerable ranges listed in the table below (for example, versions earlier than 2026.2.13), your application is affected.

Note: The npm ls openclaw command inspects dependencies declared in your package.json and lockfile; it does not perform automated runtime dynamic scanning.

Technical Details

Vulnerability Mechanism & Technical Analysis

This vulnerability is classified under CWE-345: Insufficient Verification of Data Authenticity, where the product does not sufficiently verify the origin or authenticity of data, in a way that causes it to accept invalid data. In Openclaw, software state validation or input boundaries are circumvented during processing. Review the official source advisory statement below for specific affected components, classes, and reproduction details.

Source Advisory Statement

## Summary Inter-session messages sent via `sessions_send` could be interpreted as direct end-user instructions because they were persisted as `role: "user"` without provenance metadata. ## Affected Packages / Versions - Package: `openclaw` (npm) - Affected versions: `<= 2026.2.12` (i.e. `< 2026.2.13`) - Fixed in: `2026.2.13` (patched versions `>= 2026.2.13`) ## Impact A delegated or internal session could inject instructions into another session that appeared equivalent to externally-originated user input. This is an instruction-provenance confusion issue (confused-deputy style), which can lead to unintended privileged behavior in workflows that trust `role: "user"` as a sole authority signal. ## Technical details Before the fix, routed inter-session prompts were stored as regular user turns without a verifiable source marker. As a result, downstream workers and transcript readers could not distinguish: - External user input - Internal inter-session routed input ## Fix OpenClaw now carries explicit input provenance end-to-end for routed prompts. Key changes: - Added structured provenance model (`inputProvenance`) with `kind` values including `inter_session`. - `sessions_send` and agent-to-agent steps now set inter-session provenance when invoking target runs. - Provenance is persisted on user messages as `message.provenance.kind = "inter_session"` (role remains `user` for provider compatibility). - Transcript readers and memory helpers were updated to respect provenance and avoid treating inter-session prompts as external user-originated input. - Runtime context rebuilding now annotates inter-session turns with an explicit in-memory marker (`[Inter-session message]`) for clearer model-side disambiguation. - Regression tests were added for transcript parsing, session tools flow, runner sanitization, and memory hook behavior. ## Fix Commit(s) - `85409e401b6586f83954cb53552395d7aab04797` ## Workarounds If immediate upgrade is not possible: - Disable or restrict `sessions_send` in affected environments. - Do not use role alone as an authority boundary; require provenance-aware checks in orchestration logic. ## Credit Reported by @anbecker. Thanks @anbecker for reporting.

GHSA-w5c7-9qqw-6645 Affected Openclaw Versions

1 component(s)
Fixed Versions:
2026.2.13
Product / Package Ecosystem Affected Versions Fixed Version
openclaw
npm
< 2026.2.13
2026.2.13

References

Frequently Asked Questions

What is GHSA-w5c7-9qqw-6645?
GHSA-w5c7-9qqw-6645 is a security vulnerability in Openclaw involving OpenClaw inter-session prompts could be treated as direct user instructions under CWE-345: Insufficient Verification of Data Authenticity.
Which Openclaw versions are affected?
Affected versions include releases prior to 2026.2.13 across affected packages: openclaw.
What version fixes GHSA-w5c7-9qqw-6645?
Upgrading to 2026.2.13 (or the latest patched release for your respective branch) resolves the vulnerability.
Is openclaw affected?
Yes, openclaw is affected in releases prior to 2026.2.13. Upgrade your dependency to 2026.2.13 or later.
What CWE is associated with GHSA-w5c7-9qqw-6645?
GHSA-w5c7-9qqw-6645 is classified under CWE-345: Insufficient Verification of Data Authenticity (The product does not sufficiently verify the origin or authenticity of data, in a way that causes it to accept invalid data.).
How can I check npm dependencies for GHSA-w5c7-9qqw-6645?
Run the dependency tree command: 'npm ls openclaw'. This command lists direct and transitive dependencies in your build configuration so you can verify if a vulnerable version is resolved.
Machine-readable OSV JSON OSV v1.5 Schema
Normalized schema output
{
  "schema_version" : "1.4.0",
  "id" : "GHSA-w5c7-9qqw-6645",
  "modified" : "2026-02-18T00:56:51Z",
  "published" : "2026-02-18T00:56:51Z",
  "aliases" : [ ],
  "summary" : "OpenClaw inter-session prompts could be treated as direct user instructions",
  "details" : "## Summary\n\nInter-session messages sent via `sessions_send` could be interpreted as direct end-user instructions because they were persisted as `role: \"user\"` without provenance metadata.\n\n## Affected Packages / Versions\n\n- Package: `openclaw` (npm)\n- Affected versions: `<= 2026.2.12` (i.e. `< 2026.2.13`)\n- Fixed in: `2026.2.13` (patched versions `>= 2026.2.13`)\n\n## Impact\n\nA delegated or internal session could inject instructions into another session that appeared equivalent to externally-originated user input.\n\nThis is an instruction-provenance confusion issue (confused-deputy style), which can lead to unintended privileged behavior in workflows that trust `role: \"user\"` as a sole authority signal.\n\n## Technical details\n\nBefore the fix, routed inter-session prompts were stored as regular user turns without a verifiable source marker.\n\nAs a result, downstream workers and transcript readers could not distinguish:\n- External user input\n- Internal inter-session routed input\n\n## Fix\n\nOpenClaw now carries explicit input provenance end-to-end for routed prompts.\n\nKey changes:\n- Added structured provenance model (`inputProvenance`) with `kind` values including `inter_session`.\n- `sessions_send` and agent-to-agent steps now set inter-session provenance when invoking target runs.\n- Provenance is persisted on user messages as `message.provenance.kind = \"inter_session\"` (role remains `user` for provider compatibility).\n- Transcript readers and memory helpers were updated to respect provenance and avoid treating inter-session prompts as external user-originated input.\n- Runtime context rebuilding now annotates inter-session turns with an explicit in-memory marker (`[Inter-session message]`) for clearer model-side disambiguation.\n- Regression tests were added for transcript parsing, session tools flow, runner sanitization, and memory hook behavior.\n\n## Fix Commit(s)\n\n- `85409e401b6586f83954cb53552395d7aab04797`\n\n## Workarounds\n\nIf immediate upgrade is not possible:\n- Disable or restrict `sessions_send` in affected environments.\n- Do not use role alone as an authority boundary; require provenance-aware checks in orchestration logic.\n\n## Credit\n\nReported by @anbecker.\n\nThanks @anbecker for reporting.",
  "severity" : [ {
    "type" : "CVSS_V4",
    "score" : "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:H/VA:N/SC:N/SI:N/SA:N"
  } ],
  "affected" : [ {
    "package" : {
      "ecosystem" : "npm",
      "name" : "openclaw"
    },
    "ranges" : [ {
      "type" : "ECOSYSTEM",
      "events" : [ {
        "introduced" : "0"
      }, {
        "fixed" : "2026.2.13"
      } ]
    } ]
  } ],
  "references" : [ {
    "type" : "WEB",
    "url" : "https://github.com/openclaw/openclaw/security/advisories/GHSA-w5c7-9qqw-6645"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/openclaw/openclaw/commit/85409e401b6586f83954cb53552395d7aab04797"
  }, {
    "type" : "PACKAGE",
    "url" : "https://github.com/openclaw/openclaw"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/openclaw/openclaw/releases/tag/v2026.2.12"
  } ],
  "database_specific" : {
    "cwe_ids" : [ "CWE-345" ],
    "severity" : "HIGH",
    "github_reviewed" : true,
    "github_reviewed_at" : "2026-02-18T00:56:51Z",
    "nvd_published_at" : null
  }
}