CVE-2026-82579 json
AshAi tool loop never terminates when all tool calls are filtered out, enabling denial of service
published 2026-08-31 2 mo ago modified 2026-09-08 2 mo ago also EEF-CVE-2026-82579 , EUVD-2026-68307 , GHSA-rcx7-x2w5-mmc2
- cvss
- 6.0
- version 4.0, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.5%
- EPSS 0.5% chance of exploitation in 30 days, percentile 40%
- public exploits
- 0
- none known
Summary
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.
Patch / fix
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- no
- Technical impact
- partial
- Assessed
- 2 mo ago
Exploit prediction
0.47% chance of exploitation in the next 30 days, higher than 40% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/ash-project/ash_ai/security/advisories/GHSA-rcx7-x2w5-mmc2 referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 4.0 | 6.0 | 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 |
| CNA | 4.0 | 6.0 | 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 |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| hex | ash_ai | >=0.6.0, <1.0.0 |
1.0.0 |
Affected products
- ash-project ash_ai
Classification
- Weakness
-
- CWE-835 Loop with Unreachable Exit Condition
References
-
github.com
/ash-project/ash_ai/commit/53325fdab90afab628c6a53232ef2a9001580bd9
patch
-
github.com
/ash-project/ash_ai/security/advisories/GHSA-rcx7-x2w5-mmc2
vendor-advisory, related, exploit, advisory
-
cna.erlef.org
/cves/CVE-2026-82579.html
related, web
-
osv.dev
/vulnerability/EEF-CVE-2026-82579
related
-
hex.pm
/packages/ash_ai
package
Sources
- CVE List CVE-2026-82579
- NVD CVE-2026-82579
- OSV EEF-CVE-2026-82579
Fencer Vulns 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.
CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.