Answer in brief
CVE-2026-56696 records a Medium severity (CVSS 5.4) vulnerability in OpenHarness remote project-context commands allow persistent prompt poisoning. The current sources do not mark it as known exploited. The current feed maps openharness-ai (pip), openharness-ai (pypi). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 5.4. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps openharness-ai (pip), openharness-ai (pypi). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| openharness-aipip | <=0.1.9 | Not reported |
| openharness-aipypi | >=0 | Not reported |
Published upstream
Jun 23, 2026
Evidence: source:ghsa:source_dates:source-dates:recordSource modified
Sep 4, 2026
Evidence: source:ghsa:source_dates:source-dates:recordFirst seen by HOL
Jun 23, 2026
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.
Quoted source text, attributed separately from HOL analysis.