Every CVESearch/Get API key

GHSA-w5c7-9qqw-6645

OpenClaw inter-session prompts could be treated as direct user instructions

7.1 HighFix available

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.

Attack profile

How easy it is to exploit

Attack vector
Network
Complexity
Low
Privileges needed
Low
User interaction
None

What an attacker can affect

Confidentiality
Low
Integrity
High
Availability
None

What each source reports

GitHub Advisories Score used7.1

OpenClaw inter-session prompts could be treated as direct user instructions

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.

Record
GHSA-w5c7-9qqw-6645
CVSS 4.0
7.1 HighCVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:H/VA:N/SC:N/SI:N/SA:N
Weakness
CWE-345
Updated
2026-11-02
OSV7.1

OpenClaw inter-session prompts could be treated as direct user instructions

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.

Record
GHSA-w5c7-9qqw-6645
CVSS 4.0
7.1 HighCVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:H/VA:N/SC:N/SI:N/SA:N
Weakness
CWE-345
Updated
2026-11-02

Affected packages

Affected packages
PackageAffectedFixed
openclaw
npm
before 2026.2.13
2026.2.13

History

History
RecordedChangedSources
first indexedGitHub Advisories, OSV

Dates are when Every CVE recorded each change. Upstream dates may differ.

In short

GHSA-w5c7-9qqw-6645 is a high vulnerability (CVSS 7.1) in openclaw, published February 18, 2026. No source lists public exploit code. Fixed in openclaw 2026.2.13.

References

MoveEnter Open