CVE-2026-9366 json
NousResearch hermes-agent prompt_builder.py _scan_context_content injection
published 5mo ago modified 3mo ago also GHSA-pgp4-xr4j-h5cg , PYSEC-2026-2514 , EUVD-2026-31580
- cvss
- 7.3
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.3%
- EPSS 0.3% chance of exploitation in 30 days, percentile 23%
- public exploits
- 0
- none known
Summary
A vulnerability was found in NousResearch hermes-agent 2026.4.23. The impacted element is the function _scan_context_content of the file agent/prompt_builder.py. The manipulation results in injection. The attack may be performed from remote. The exploit has been made public and could be used. The vendor was contacted early about this disclosure but did not respond in any way.
Patch / fix
Is CVE-2026-9366 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.
Check with FencerCISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- yes
- Technical impact
- partial
- Assessed
- 5mo ago
Exploit prediction
0.31% chance of exploitation in the next 30 days, higher than 23% of all scored CVEs (FIRST EPSS, 2026-11-11).
Exploits and checks
- gist.github.com https://gist.github.com/YLChen-007/581fd92de5548fbaacb2092e848a75cc referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 4.0 | 6.9 | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P |
| CNA | 3.1 | 7.3 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R |
| CNA | 3.0 | 7.3 | CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R |
| CNA | 2.0 | 7.5 | AV:N/AC:L/Au:N/C:P/I:P/A:P/E:POC/RL:ND/RC:UR |
| CNA | 4.0 | 5.5 | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X |
| CNA | 3.1 | 7.3 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L |
| CNA | 2.0 | 7.5 | AV:N/AC:L/Au:N/C:P/I:P/A:P |
| GitHub | 3.1 | 7.3 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L |
| OSV | 3.1 | 7.3 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | hermes-agent | <0.15.0 |
0.15.0 |
Affected products
- NousResearch hermes-agent
Classification
References
-
github.com
/NousResearch/hermes-agent/commit/0dee92df22bdc0cfbcad90ca954aa14916f018de
web
-
gist.github.com
/YLChen-007/581fd92de5548fbaacb2092e848a75cc
exploit, web
-
vuldb.com
/vuln/365329
vdb-entry, technical-description, web
-
vuldb.com
/vuln/365329/cti
signature, permissions-required, web
-
vuldb.com
/submit/812227
third-party-advisory, web
-
nvd.nist.gov
/vuln/detail/CVE-2026-9366
advisory
-
github.com
/NousResearch/hermes-agent
package
-
pypi.org
/project/hermes-agent
package
-
github.com
/advisories/GHSA-pgp4-xr4j-h5cg
advisory
Sources
- CVE List CVE-2026-9366
- GitHub Advisory GHSA-pgp4-xr4j-h5cg
- NVD CVE-2026-9366
- OSV PYSEC-2026-2514
Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.