hkuds/openharness · Security
OpenHarness remote project-context commands allow persistent prompt poisoning
- GHSA ID
- GHSA-24cw-228q-3rx9
- CVE ID
- CVE-2026-56696
- Severity
- medium
- Published
- Updated
- CVSS
- 5.4 · CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:N
- CVSS v3
- 5.4 · CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:N
- CVSS v4
- 5.3 · CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N
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.
CWEs
- CWE-862 · Missing Authorization
References
- https://nvd.nist.gov/vuln/detail/CVE-2026-56696 ↗
- https://github.com/HKUDS/OpenHarness/pull/272 ↗
- https://github.com/HKUDS/OpenHarness/commit/27bb93b810e9ea8fa4832eab7152eeb3b4a6bffb ↗
- https://www.vulncheck.com/advisories/openharness-prompt-injection-via-issue-and-pr-comments-slash-commands ↗
- https://github.com/advisories/GHSA-24cw-228q-3rx9 ↗