CVE-2026-56696 OpenHarness - Prompt Injection via /issue and /pr_comments Slash Commands
Remote attackers can inject malicious Markdown into agent context files via slash commands, leading to persistent prompt injection and potential code execution.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-56696?
CVE-2026-56696 is a medium-severity code injection vulnerability in HKUDS OpenHarness, published on 23 Jun 2026. Any signed-in user can exploit it over the network, with no action from the victim.
Official 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.
Weakness: CWE-862
Which versions are affected by CVE-2026-56696?
3 open source packages ship an affected version, including openharness-ai.
| Package | Affected | Fixed in |
|---|---|---|
openharness-ai PyPI | All versions to 0.1.9 | None |
openharness-ai PyPI | All versions to 0.1.9 | None |
openharness-ai PyPI | All versions to 0.1.9 | None |
How do I fix CVE-2026-56696?
No fix has been published for CVE-2026-56696 yet. Limit exposure of the affected software until one is available.
Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.
Is CVE-2026-56696 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-56696 exists.
Sources
Also known as GHSA-24cw-228q-3rx9, PYSEC-2026-3880.