CVE-2026-9366: NousResearch hermes-agent prompt_builder.py _scan_context_content injection
Noroxi assessment
Priority: Monitor (action score 22/100)
- The sources we track (CISA KEV, Exploit-DB, Metasploit, Nuclei, GitHub) show no public exploit code or exploitation in the wild.
- Probability of exploitation in the next 30 days: 0.30% (FIRST EPSS).
- Anyone who can reach it over the internet can trigger it. No account or password is required. No user action is required. No special conditions are required; it is repeatable.
- According to CISA the attack is automatable: targets can be found by mass scanning.
- Fixed version: hermes-agent (PyPI) 0.15.0.
Low priority for now. Upgrade to hermes-agent (PyPI) 0.15.0 or later.
Generated automatically from the record's data: CVSS (NVD and CNA), CISA KEV and SSVC, FIRST EPSS, exploit sources, fixed versions. How we calculate it
Primary sources: NVD · CVE.org · FIRST EPSS
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.
- Published
- May 24, 2026
- Updated
- Jul 23, 2026
- EPSS
- 0.3% · 23th percentile
- CWE
- CWE-74
Report tools
Action score
22
Low priority for now.
- CVSS
- 22 / 40 · 5.5 / 10
- CISA KEV
- 0 / 30 · Not listed
- EPSS
- 0 / 30 · 0.3%
CISA SSVC decision
- Exploitation
- proof of concept
- Automatable
- yes
- Technical impact
- partial
Vulnrichment: CISA's decision-tree inputs.
CNA vs NVD score
- NVD
- —
- CNA · VulDB
- 6.9
- NVD has not scored this yet; the score shown is the CNA’s.
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
The score given by the assigning authority versus NVD’s independent score. A gap means the severity is contested.
Get told when this record changes
- Not in KEV: no record of exploitation in the wild
- No public exploit code on record
- A fix has been released
If any of these changes, we'll tell you in the daily email digest.
Is your version affected? Check itNoroxi analysis
What does it mean in your environment?
The assessment above is generated automatically from the record's data; it doesn't know your environment. Our team verifies on your systems whether this vulnerability is actually exploitable and which mitigation is enough.
We use this product, ask for helpAffected systems
Is your version affected?
Pick the product and type the version you run. It's compared with this record's version ranges in your browser; the version isn't sent anywhere.
—
Versions reported by the vendor
Affected version ranges reported by the assigning authority (VulDB). Independent of NVD's CPE analysis and usually ahead of it.
NousResearch hermes-agent
- 2026.4.23affected
Package-level exposure
OSV and GitHub Advisory data: ecosystem, package and range. SBOM matching uses this table.
| Ecosystem | Package | Affected range | Fix |
|---|---|---|---|
| PyPI | hermes-agent | before 0.15.0 | 0.15.0 |
Same product
nousresearch: all recordsOther highest-scoring records for the same primary product.
- CVE-2026-82021Hermes Agent 0.18.2 < 0.19.0 MCP Catalog Supply Chain RCE via Mutable Branch Reference36Monitor
- CVE-2026-71963Hermes Agent 0.18.2 - 0.21.0 RCE via git core.fsmonitor Config Injection34Monitor
- CVE-2026-53869Hermes Agent < 0.16.0 - DNS Rebinding Bypass via WebSocket Endpoints34Monitor
Published before and after this one in the same product
- ← EarlierCVE-2026-9353May 24, 2026 · NousResearch hermes-agent Skills Guard Multi-Word Prompt skills_guard.py injection22Monitor
- ← EarlierCVE-2026-9354May 24, 2026 · NousResearch hermes-agent Slack Agent/Mattermost Agent escape output22Monitor
- Later →CVE-2026-9367May 24, 2026 · NousResearch hermes-agent terminal_tool approval.py detect_dangerous_command os command injection23Monitor
Remediation
Which version to upgrade to
Fix versions compiled from the vendor, package registries and Microsoft. Verify the vendor's note before upgrading.
| Product / package | Fixed version | Source |
|---|---|---|
| PyPI:hermes-agent | 0.15.0 | Package registry (OSV) |
Exploit status
No known public exploit
No public exploit has been observed yet. That doesn't mean you're safe, only that the bar is a little higher.
Research context
For pentesters and researchers: attack profile, score disagreement, timeline, patch commits, credits, variant and chain candidates, bug bounty scope. All derived from existing data; no exploit code.
Timeline
From publication to today: proof of concept, Metasploit module, CISA KEV and fix record. Dates are as reported by the sources.
No dated events beyond publication.
Credits
All researchersFinders, reporters and analysts named in the CNA record. Click a name for that researcher’s other records.
- Eric-i (VulDB User)reporter
- VulDB CNA Teamcoordinator
Variant candidates
Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.
- CVE-2026-93530 days apartNousResearch hermes-agent Skills Guard Multi-Word Prompt skills_guard.py injection22Monitor
- CVE-2026-93540 days apartNousResearch hermes-agent Slack Agent/Mattermost Agent escape output22Monitor
- CVE-2026-102208 days apartNousResearch hermes-agent skills_tool.py skill_view injection22Monitor
- CVE-2026-102218 days apartNousResearch hermes-agent run_agent.py _compress_context injection22Monitor
- CVE-2026-102228 days apartNousResearch hermes-agent config.py _sanitize_env_lines injection11Monitor
- CVE-2026-102238 days apartNousResearch hermes-agent memory_tool.py _scan_memory_content injection8Monitor
Not on record for this CVE: EPSS history · patch commit or PR link · public bounty program.
Technical details
Attack conditions
- Anyone who can reach it over the internet can trigger it.
- No account or password is required.
- No user action is required.
- No special conditions are required; it is repeatable.
If successful
- Confidentiality
- Integrity
- Availability
- Attack vector
- Network
- Attack complexity
- Low
- Privileges required
- None
- User interaction
- None
- Scope
- X
Weakness class (CWE)
CWE-74 · Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')CVSS vector
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
nvd-secondary
Attack context
MITRE CAPEC attack patterns and ATT&CK techniques for this weakness class (CWE). A starting point for detection rules and threat hunting.
Attack patterns (CAPEC)
- Buffer Overflow via Environment VariablesCAPEC-10likelihood: High · High
- Server Side Include (SSI) InjectionCAPEC-101likelihood: High · High
- HTTP Request SplittingCAPEC-105likelihood: Medium · High
- Command Line Execution through SQL InjectionCAPEC-108likelihood: Low · Very High
- Double EncodingCAPEC-120likelihood: Low · Medium
- Subverting Environment Variable ValuesCAPEC-13likelihood: High · Very High
- Format String InjectionCAPEC-135likelihood: High · High
- Client-side Injection-induced Buffer OverflowCAPEC-14likelihood: Medium · High
Change log (1)
- Fix✗ → ✓
For records you follow, these changes also arrive as notifications. →
References
Show all references (3 more)Show less
Vendor advisories and official records. Exploit/PoC links are deliberately left out.