GitHub Advisoryadvisory · PyPI
GHSA-24cw-228q-3rx9 OpenHarness remote project-context commands allow persistent prompt poisoning
MEDIUM
Official page ↗
- Aliases
- CVE-2026-56696
- Ecosystem
- PyPI
- Packages
- openharness-ai
- Severity
- Moderate
- CVSS vector
- CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:N
- Weaknesses
- CWE-862
- Reviewed
- 2026-09-04
Affected packages
• PyPI openharness-ai: <= 0.1.9 (no fix yet)
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.
Related
Alias · CVE (1)
- CVE-2026-56696 OpenHarness /issue and /pr_comments slash commands lack remote_invocable=False protection, allowing remote channel senders to write… vulnerability
Weakness · CWE (1)
- CWE-862 Missing Authorization weakness
References
- 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