GHSA-w5c7-9qqw-6645: OpenClaw inter-session prompts could be treated as direct user instructions
Noroxi assessment
Priority: Monitor (action score 0/100)
- The sources we track (CISA KEV, Exploit-DB, Metasploit, Nuclei, GitHub) show no public exploit code or exploitation in the wild.
- Anyone who can reach it over the internet can trigger it. A low-privileged account is enough. No user action is required. No special conditions are required; it is repeatable.
- Fixed version: openclaw (npm) 2026.2.13.
Low priority for now. Upgrade to openclaw (npm) 2026.2.13 or later.
Generated automatically from the record's data: CVSS (NVD and CNA), CISA KEV and SSVC, FIRST EPSS, exploit sources, fixed versions. How we calculate it
Primary sources: OSV
## 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.
- Published
- Feb 18, 2026
- Updated
- Feb 18, 2026
- EPSS
- —
- CWE
- CWE-345
Report tools
Action score
0
Low priority for now.
- CVSS
- 0 / 40 · —
- CISA KEV
- 0 / 30 · Not listed
- EPSS
- 0 / 30 · —
Get told when this record changes
- Not in KEV: no record of exploitation in the wild
- No public exploit code on record
- A fix has been released
If any of these changes, we'll tell you in the daily email digest.
Is your version affected? Check itNoroxi analysis
What does it mean in your environment?
The assessment above is generated automatically from the record's data; it doesn't know your environment. Our team verifies on your systems whether this vulnerability is actually exploitable and which mitigation is enough.
We use this product, ask for helpAffected systems
Is your version affected?
Pick the product and type the version you run. It's compared with this record's version ranges in your browser; the version isn't sent anywhere.
| Vendor | Product | CPE |
|---|---|---|
| npm | openclaw | pkg:npm/openclaw |
Package-level exposure
OSV and GitHub Advisory data: ecosystem, package and range. SBOM matching uses this table.
| Ecosystem | Package | Affected range | Fix |
|---|---|---|---|
| npm | openclaw | before 2026.2.13 | 2026.2.13 |
Same product
npm: all recordsOther highest-scoring records for the same primary product.
- GHSA-943q-mwmv-hhvhOpenClaw: Gateway /tools/invoke tool escalation + ACP permission auto-approval35Monitor
- GHSA-474h-prjg-mmw3OpenClaw: Sandboxed sessions_spawn(runtime="acp") bypassed sandbox inheritance and allowed host ACP initialization32Monitor
- GHSA-56f2-hvwg-5743OpenClaw affected by SSRF in Image Tool Remote Fetch30Monitor
Published before and after this one in the same product
- ← EarlierGHSA-g27f-9qjv-22pmFeb 17, 2026 · OpenClaw log poisoning (indirect prompt injection) via WebSocket headers12Monitor
- ← EarlierGHSA-chm2-m3w2-wcxmFeb 17, 2026 · OpenClaw Google Chat spoofing access with allowlist authorized mutable email principal despite sender-ID mismatch0Monitor
- Later →GHSA-392f-ggf5-fp3cMar 2, 2026 · OpenClaw: Unicode canonicalization drift in node metadata policy classification could broaden node allowlists0Monitor
Remediation
Which version to upgrade to
Fix versions compiled from the vendor, package registries and Microsoft. Verify the vendor's note before upgrading.
| Product / package | Fixed version | Source |
|---|---|---|
| npm:openclaw | 2026.2.13 | Package registry (OSV) |
Exploit status
No known public exploit
No public exploit has been observed yet. That doesn't mean you're safe, only that the bar is a little higher.
Research context
For pentesters and researchers: attack profile, score disagreement, timeline, patch commits, credits, variant and chain candidates, bug bounty scope. All derived from existing data; no exploit code.
Timeline
From publication to today: proof of concept, Metasploit module, CISA KEV and fix record. Dates are as reported by the sources.
No dated events beyond publication.
Patch and commit links
Commit, PR and diff links among the references. A starting point for patch-diffing and variant hunting; fixes, not exploits.
Not on record for this CVE: EPSS history · researcher credit · variant or chain candidate · public bounty program.
Technical details
Attack conditions
- Anyone who can reach it over the internet can trigger it.
- A low-privileged account is enough.
- No user action is required.
- No special conditions are required; it is repeatable.
If successful
- Confidentiality
- Integrity
- Availability
- Attack vector
- Network
- Attack complexity
- Low
- Privileges required
- Low
- User interaction
- None
Weakness class (CWE)
CWE-345 · Insufficient Verification of Data AuthenticityCVSS vector
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
osv
Attack context
MITRE CAPEC attack patterns and ATT&CK techniques for this weakness class (CWE). A starting point for detection rules and threat hunting.
Attack patterns (CAPEC)
- JSON Hijacking (aka JavaScript Hijacking)CAPEC-111likelihood: High · High
- Cache PoisoningCAPEC-141likelihood: High · High
- DNS Cache PoisoningCAPEC-142likelihood: High · High
- Content SpoofingCAPEC-148likelihood: Medium · Medium
- Spoofing of UDDI/ebXML MessagesCAPEC-218Medium
- Application API Message Manipulation via Man-in-the-MiddleCAPEC-384Low
- Transaction or Event Tampering via Application API ManipulationCAPEC-385Medium
- Application API Navigation RemappingCAPEC-386Medium
Change log (2)
- Fix✗ → ✓
- CVSS8 → —
For records you follow, these changes also arrive as notifications. →
References
Show all references (3 more)Show less
Vendor advisories and official records. Exploit/PoC links are deliberately left out.