CVE-2026-56696: Missing Authorization in HKUDS OpenHarness
OpenHarness /issue and /pr_comments slash commands lack remote_invocable=False protection, allowing remote channel senders to write attacker-controlled Markdown into project context files. Admitted remote attackers can inject malicious content into .openharness/issue.md and .openharness/pr_comments.md files, which are subsequently injected into runtime system prompts, persistently influencing local agent behavior.
AI Analysis
Technical Summary
The vulnerability in HKUDS OpenHarness involves missing authorization controls on the /issue and /pr_comments slash commands, which do not have remote_invocable=False protection. This allows remote channel senders to write arbitrary Markdown content into .openharness/issue.md and .openharness/pr_comments.md files. Since these files are injected into runtime system prompts, the injected content can persistently affect the behavior of the local agent. The affected versions are all versions up to and including 0.1.9. There is no official remediation or patch available as of the published date.
Potential Impact
An attacker with remote access to the affected slash commands can inject malicious Markdown content into project context files that are later used in runtime system prompts. This persistent injection can influence the behavior of the local agent, potentially leading to unauthorized actions or manipulation of system operations. The vulnerability has a CVSS 4.0 base score of 5.3, indicating a medium severity impact with network attack vector, low complexity, and no user interaction required.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is released, restrict access to the affected slash commands to trusted users only and monitor for suspicious activity related to the injection of Markdown content into the .openharness directory. Avoid exposing these commands to untrusted remote channels.
CVE-2026-56696: Missing Authorization in HKUDS OpenHarness
Description
OpenHarness /issue and /pr_comments slash commands lack remote_invocable=False protection, allowing remote channel senders to write attacker-controlled Markdown into project context files. Admitted remote attackers can inject malicious content into .openharness/issue.md and .openharness/pr_comments.md files, which are subsequently injected into runtime system prompts, persistently influencing local agent behavior.
CVSS v4.0
Score 5.3medium
Affected software
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
The vulnerability in HKUDS OpenHarness involves missing authorization controls on the /issue and /pr_comments slash commands, which do not have remote_invocable=False protection. This allows remote channel senders to write arbitrary Markdown content into .openharness/issue.md and .openharness/pr_comments.md files. Since these files are injected into runtime system prompts, the injected content can persistently affect the behavior of the local agent. The affected versions are all versions up to and including 0.1.9. There is no official remediation or patch available as of the published date.
Potential Impact
An attacker with remote access to the affected slash commands can inject malicious Markdown content into project context files that are later used in runtime system prompts. This persistent injection can influence the behavior of the local agent, potentially leading to unauthorized actions or manipulation of system operations. The vulnerability has a CVSS 4.0 base score of 5.3, indicating a medium severity impact with network attack vector, low complexity, and no user interaction required.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is released, restrict access to the affected slash commands to trusted users only and monitor for suspicious activity related to the injection of Markdown content into the .openharness directory. Avoid exposing these commands to untrusted remote channels.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulnCheck
- Date Reserved
- 2026-06-22T17:09:16.556Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a3aafb1eed863c81e44dd93
Added to database: 06/23/2026, 16:09:21 UTC
Last enriched: 06/23/2026, 16:24:29 UTC
Last updated: 06/23/2026, 20:07:17 UTC
Views: 6
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.