CVE-2026-82579: AshAi tool loop never terminates when all tool calls are filtered out, enabling denial of service
Noroxi assessment
Priority: Monitor (action score 24/100)
- 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: 0.46% (FIRST EPSS).
- Anyone who can reach it over the internet can trigger it. A low-privileged account is enough. No user action is required. No special conditions are required; it is repeatable.
- Fixed version: ash-project ash_ai 1.0.0, 53325fdab90afab628c6a53232ef2a9001580bd9.
Low priority for now. Upgrade to ash-project ash_ai 1.0.0, 53325fdab90afab628c6a53232ef2a9001580bd9 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
Loop with Unreachable Exit Condition (Infinite Loop) vulnerability in ash-project ash_ai allows an attacker who can influence a model's output to hang the tool loop and drive unbounded, repeated model requests. AshAi.ToolLoop classifies a model response of :tool_calls, then filters the calls through normalize_tool_calls/2 and unprocessed_tool_calls/2. Both can empty the list: a call missing a valid name, or one reusing a tool_call_id that already has a result in history, is dropped. With an empty list the loop appended nothing and recursed with a byte-identical message list, so the conversation never advanced and the same request was re-sent every iteration. Under the supported max_iterations: :infinity this never terminated; otherwise it exhausted the full budget. Prompt-injected content can make the model re-emit a spent tool_call_id. The fix treats an empty post-filter list as terminal. This issue affects ash_ai: from 0.6.0 before 1.0.0.
- Published
- Aug 30, 2026
- Updated
- Sep 1, 2026
- EPSS
- 0.4% · 40th percentile
- CWE
- CWE-835
Report tools
Action score
24
Monitor
Low priority for now.
- CVSS
- 24 / 40 · 6.0 / 10
- CISA KEV
- 0 / 30 · Not listed
- EPSS
- 0 / 30 · 0.4%
CISA SSVC decision
- Exploitation
- proof of concept
- Automatable
- no
- Technical impact
- partial
Vulnrichment: CISA's decision-tree inputs.
CNA vs NVD score
- NVD
- —
- CNA · EEF
- 6.0
- NVD has not scored this yet; the score shown is the CNA’s.
CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
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 (EEF). Independent of NVD's CPE analysis and usually ahead of it.
ash-project ash_ai
- 0.6.0 and later · before 1.0.0affected · semver
- bc2122f78fca6c11d8ec2b9ac53148ec17476460 and later · before 53325fdab90afab628c6a53232ef2a9001580bd9affected · git
Package-level exposure
OSV and GitHub Advisory data: ecosystem, package and range. SBOM matching uses this table.
| Ecosystem | Package | Affected range | Fix |
|---|---|---|---|
| Hex | ash_ai | from 0.6.0 · before 1.0.0 | 1.0.0 |
Same product
ash-project: all recordsOther highest-scoring records for the same primary product.
- CVE-2026-77956EEx template evaluation of prompt content in AshAi enables remote code execution35Monitor
- CVE-2026-81315MCP DNS-rebinding origin check in AshAi is bypassed by a spoofed X-Forwarded-Proto header29Monitor
- CVE-2026-82564Identity tool filter in AshAi accepts operator maps, allowing update or destroy of unidentified records28Monitor
Published before and after this one in the same product
- ← EarlierCVE-2026-75760Aug 30, 2026 · AshAi vectorize change leaks raw embedding-provider errors, including credentials, in a user-facing error28Monitor
- Later →CVE-2026-82580Aug 30, 2026 · AshAi echoes raw tool exception messages into the conversation, disclosing internal details21Monitor
- Later →CVE-2026-78230Sep 8, 2026 · AshAi aggregate tool can read field-policy-protected fields24Monitor
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 |
|---|---|---|
| ash-project ash_ai | 1.0.0 | Vendor (CNA) |
| ash-project ash_ai | 53325fdab90afab628c6a53232ef2a9001580bd9 | Vendor (CNA) |
| Hex:ash_ai | 1.0.0 | 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.
FIRST EPSS daily score; only changes of 0.01 or more are recorded (step chart).
Patch and commit links
Commit, PR and diff links among the references. A starting point for patch-diffing and variant hunting; fixes, not exploits.
Credits
All researchersFinders, reporters and analysts named in the CNA record. Click a name for that researcher’s other records.
- Peter Ullrichfinder
- Zach Daniel / Ash Projectremediation developer
- Jonatan Männchen / EEFcoordinator
Variant candidates
Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.
No nightly-computed relations.
Chain candidates
An authentication bypass and a privilege-requiring bug in the same product, published close together: combined they may become an unauthenticated path.
—
Bug bounty scope
No known public program.
Source: bounty-targets-data (public HackerOne, Bugcrowd, Intigriti, YesWeHack listings).
Technical details
Attack conditions
- Anyone who can reach it over the internet can trigger it.
- A low-privileged account is enough.
- 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
- Low
- User interaction
- None
- Scope
- X
Weakness class (CWE)
CWE-835 · Loop with Unreachable Exit Condition ('Infinite Loop')CVSS vector
CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/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.
MITRE has no CAPEC/ATT&CK mapping for this CWE.
Change log
- 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.