PatchSiren cyber security CVE debrief
CVE-2026-108789 deepseek-ai CVE debrief
A vulnerability was identified in deepseek-ai deepseek-harness up to 0.1.1-rc.2. This affects the function agent of the component dsh-workflow-worker-thread. The manipulation leads to enforcement of behavioral workflow. The attack is possible to be carried out remotely. The exploit is publicly available and might be used. Defenders should assess exposure and prioritize verification of affected versions in their environments due to publicly available exploits and potential behavioral workflow enforcement.
- Vendor
- deepseek-ai
- Product
- deepseek-harness
- CVSS
- LOW 2
- CISA KEV
- Not listed in stored evidence
- Original CVE published
- 2026-10-12
- Original CVE updated
- 2026-10-12
- Advisory published
- 2026-10-12
- Advisory updated
- 2026-10-12
Who should care
Defenders responsible for deepseek-harness deployments should assess exposure and prioritize verification of affected versions in their environments due to publicly available exploits and potential behavioral workflow enforcement. This includes operators, platform administrators, vulnerability management teams, and security teams who need to verify affected versions, assess exposure, and monitor for publicly available exploits.
Why it matters
Defenders should prioritize verifying the affected versions of deepseek-harness and assessing exposure in their environments due to the publicly available exploit and potential for behavioral workflow enforcement.
- Verify affected versions of deepseek-harness in use.
- Assess exposure in environments using deepseek-harness.
- Monitor for publicly available exploits.
Technical summary
The vulnerability affects the function agent of the component dsh-workflow-worker-thread in deepseek-ai deepseek-harness up to 0.1.1-rc.2, allowing for enforcement of behavioral workflow. Defenders should prioritize verifying affected versions and assessing exposure in their environments due to publicly available exploits and potential behavioral workflow enforcement. The attack is possible to be carried out remotely, and defenders should review compensating controls for exposed systems while remediation is scheduled and verified.
Defensive priority
Defenders should prioritize verifying the affected versions of deepseek-harness and assessing exposure in their environments.
Recommended defensive actions
- Verify the version of deepseek-harness in use and check if it is affected (up to 0.1.1-rc.2).
- Assess exposure in environments using deepseek-harness.
- Monitor for publicly available exploits and consider compensating controls.
- Review relevant monitoring, detection, and logs for exposed assets that need extra review.
- Track exceptions, retest remediated assets, and close the item only after evidence is documented.
- Confirm whether affected product deployments exist in managed environments and assign an owner for follow-up.
- Review the supplied official advisory or CVE record to validate affected scope, severity, and vendor guidance.
Evidence notes
The CVE record and source item provide details about the vulnerability, but the corpus lacks specific information on exploitation, impact, and remediation. Defenders should verify affected versions of deepseek-harness, assess exposure, and monitor for publicly available exploits. The source details are limited, so explicit evidence-limit language and defensive verification tasks are necessary.
Sources and references
Verified primary and authoritative sources
-
CVE-2026-108789 CVE Program record
Publisher, destination, and source semantics verified
URL: https://www.cve.org/CVERecord?id=CVE-2026-108789
CVE Program - Official CVE Program record with source-provided CVE metadata.
-
CVE-2026-108789 NVD vulnerability detail
Publisher, destination, and source semantics verified
URL: https://nvd.nist.gov/vuln/detail/CVE-2026-108789
NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.
Supplemental references
-
deepseek-ai deepseek-harness dsh-workflow-worker-thread agent behavioral workflow
Unverified legacy reference
URL: https://raw.githubusercontent.com/CVEProject/cvelistV5/main/cves/2026/108xxx/CVE-2026-108789.json
cve_program_cvelist_v5
-
Source reference
Unverified legacy reference
URL: https://vuldb.com/vuln/416568
Supplemental source - vdb-entry, technical-description
-
Source reference
Unverified legacy reference
URL: https://vuldb.com/vuln/416568/cti
Supplemental source - signature, permissions-required
-
Source reference
Unverified legacy reference
URL: https://vuldb.com/cve/CVE-2026-108789
Supplemental source - third-party-advisory
-
Source reference
Unverified legacy reference
URL: https://vuldb.com/submit/959699
Supplemental source - third-party-advisory
-
Source reference
Unverified legacy reference
URL: https://github.com/deepseek-ai/deepseek-harness/discussions/243
Supplemental source - related
-
Source reference
Unverified legacy reference
URL: https://mcniyfj5bw9b.feishu.cn/docx/M5H6d9AbioNftYxwk9CchJgGnHc
Supplemental source - exploit
-
Source reference
Unverified legacy reference
URL: https://github.com/deepseek-ai/deepseek-harness/
Supplemental source - product
Methodology and review provenance
AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.