OpenHarness - Prompt Injection via /issue and /pr_comments Slash Commands
Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).
| Vendor | Product | Default status | Versions | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| HKUDS | OpenHarness | unaffected |
|
No data.
No data.
| Vendor | Product | Versions | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Hkuds | Openharness |
|
| Source | ID | Title |
|---|---|---|
Github GHSA |
GHSA-24cw-228q-3rx9 | OpenHarness remote project-context commands allow persistent prompt poisoning |
No CVSS v3.0
No CVSS v2
This CVE is not in the KEV list.
Exploit prediction score: < 1% (0.370% probability within 30 days)
| Type | Values Removed | Values Added |
|---|---|---|
| Metrics |
ssvc
|
| Type | Values Removed | Values Added |
|---|---|---|
| CPEs | cpe:2.3:a:hkuds:openharness:*:*:*:*:*:*:*:* |
| Type | Values Removed | Values Added |
|---|---|---|
| First Time appeared |
Hkuds
Hkuds openharness |
|
| Vendors & Products |
Hkuds
Hkuds openharness |
| Type | Values Removed | Values Added |
|---|---|---|
| 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. | |
| Title | OpenHarness - Prompt Injection via /issue and /pr_comments Slash Commands | |
| Weaknesses | CWE-862 | |
| References |
| |
| Metrics |
cvssV3_1
|