🛡️ GHSA-w5c7-9qqw-6645 — openclaw
Description
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) withkindvalues includinginter_session. sessions_sendand 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 remainsuserfor 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_sendin 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.
How this vulnerability can be exploited
This issue can be reached over the network, attack complexity is low, an attacker needs low-level privileges on the target. No user interaction is required. Rated impact: confidentiality low, integrity high, availability none.
Weakness class
GHSA-w5c7-9qqw-6645 is classified as CWE-345: Insufficient Verification of Data Authenticity. Data is trusted without confirming it really came from the claimed source and was not altered.
Affected software
GHSA-w5c7-9qqw-6645 is recorded against 1 package.
- openclaw
Timeline and source
Published on 18 February 2026. No public exploit is currently recorded for this entry. Record sourced from OSV.
References
github.com (Web)
github.com (Web)
github.com (Package)
github.com (Web)
Details
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 Packages
| Software | From version | Fixed in |
|---|---|---|
| openclaw | — | — |
References
Similar Threats
- Critical CVE-2026-22172
- Medium CVE-2026-22170
- Medium CVE-2026-22169
- High CVE-2026-22171
- Medium CVE-2026-22174
More GHSA W advisories
Browse all of GHSA W in the advisory index.
- GHSA-w2wj-hw98-233h
- GHSA-w3hv-x4fp-6h6j
- GHSA-w3vw-ccc5-qr8v
- GHSA-w4c6-7r69-w7j9
- GHSA-w4f8-fxq2-j35v
- GHSA-w4hv-vmv9-hgcr
- GHSA-w4hw-qcx7-56pr
- GHSA-w4x6-hh3x-wjrx
- GHSA-w5cr-2qhr-jqc5
- GHSA-w5mj-j45q-m638
- GHSA-w5p8-4jcx-2j6r
- GHSA-w5pp-99ch-qj29
- GHSA-w5w5-8vfh-xcjq
- GHSA-w5w5-2882-47pc
- GHSA-w5xm-mx47-v7c8
- GHSA-w6f4-3v35-qjhj
Site Security Check
Is openclaw part of your stack?
GHSA-w5c7-9qqw-6645 is rated CVSS 8.0 High. BotEraser scans your installation against known CVE records and tells you whether this vulnerability applies to the versions you actually run.
Scan My Site Free →No credit card required · Results in minutes
ⓘ Data Notice: The information presented above has been compiled from publicly available internet sources. Boteraser aggregates this data solely for informational purposes and does not independently classify, evaluate, or endorse any findings about the vulnerabilities listed. The accuracy and completeness of this information is the sole responsibility of the original publishers. Boteraser and its operators accept no liability for any decisions made based on this data.