GHSA-24cw-228q-3rx9

OpenHarness remote project-context commands allow persistent prompt poisoning

Source: GitHub Advisory Database (reviewed) Moderate CVE-2026-56696

Packages

Ecosystem	Package	Affected	Fixed in
PyPI	openharness-ai	<= 0.1.9	no fix listed

Details

As written in the advisory (Markdown source, shown as plain text).

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.

References

External links from the advisory. They lead to third-party sites.

https://nvd.nist.gov/vuln/detail/CVE-2026-56696 advisory
https://github.com/HKUDS/OpenHarness/pull/272 web
https://github.com/HKUDS/OpenHarness/commit/27bb93b810e9ea8fa4832eab7152eeb3b4a6bffb web
https://github.com/HKUDS/OpenHarness package
https://www.vulncheck.com/advisories/openharness-prompt-injection-via-issue-and-pr-comments-slash-commands web