AshAi tool loop never terminates when all tool calls are filtered out, enabling denial of service
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.
- Products
- Not specified
- Affected versions
- Not specified
- Fixed versions
- Not specified
- CVEs
- CVE-2026-82579
- Confirmed fixed CVEs
- Not specified
- Updated in this feed
- 4 Nov 2026, 17:20 UTC · Revision 1
Source evidence
AshAi tool loop never terminates when all tool calls are filtered out, enabling denial of service
core-osv · Original sourcePublished 31 Aug 2026, 01:07 UTC
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.
osv:CVE-2026-82579
Complete source record
{
"id": "b46619b9e3415b910a064a93260191d263092491ad33c53047938e2ca603baa9",
"url": "https://osv.dev/vulnerability/CVE-2026-82579",
"method": "structured",
"payload": {
"kind": "advisory",
"title": "AshAi tool loop never terminates when all tool calls are filtered out, enabling denial of service",
"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.",
"evidence": "osv:CVE-2026-82579",
"products": [],
"severity": "medium",
"structured": {
"id": "CVE-2026-82579",
"aliases": [
"CVE-2026-82579",
"EEF-CVE-2026-82579",
"GHSA-rcx7-x2w5-mmc2"
],
"metrics": [
{
"type": "CVSS_V4",
"score": "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"
}
],
"affected": [
{
"ranges": [
{
"repo": "https://github.com/ash-project/ash_ai",
"type": "GIT",
"events": [
{
"introduced": "bc2122f78fca6c11d8ec2b9ac53148ec17476460"
},
{
"fixed": "53325fdab90afab628c6a53232ef2a9001580bd9"
},
{
"introduced": "c31e6f4b619d9e6f79088fdf4f2a3463941137a6"
},
{
"fixed": "f72b14744996e71df6d73480d617d963f340597b"
}
],
"database_specific": {
"extracted_events": [
{
"range": [
{
"introduced": "bc2122f78fca6c11d8ec2b9ac53148ec17476460"
},
{
"fixed": "53325fdab90afab628c6a53232ef2a9001580bd9"
}
],
"source": "AFFECTED_FIELD",
"strategy": "StandardRange"
},
{
"range": [
{
"introduced": "0.6.0"
},
{
"fixed": "1.0.0"
}
],
"source": "AFFECTED_FIELD",
"strategy": "StandardRange"
},
{
"range": [
{
"fixed": "53325fdab90afab628c6a53232ef2a9001580bd9"
}
],
"source": "REFERENCES_COMMIT"
}
]
}
}
],
"versions": [
"v0.8.2",
"v0.8.1",
"v0.8.0",
"v0.7.3",
"v0.7.2",
"v0.7.1",
"v0.7.0",
"v0.6.1",
"v0.6.0"
],
"database_specific": {
"source": "https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-82579.json"
}
}
],
"modified": "2026-10-28T02:30:37.768572287Z",
"provider": "osv",
"references": [
"https://cna.erlef.org/cves/CVE-2026-82579.html",
"https://github.com",
"https://osv.dev/vulnerability/EEF-CVE-2026-82579",
"https://repo.hex.pm",
"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/82xxx/CVE-2026-82579.json",
"https://github.com/ash-project/ash_ai/security/advisories/GHSA-rcx7-x2w5-mmc2",
"https://nvd.nist.gov/vuln/detail/CVE-2026-82579",
"https://github.com/ash-project/ash_ai/commit/53325fdab90afab628c6a53232ef2a9001580bd9",
"https://github.com/ash-project/ash_ai"
],
"provider_metadata": {
"cwe_ids": [
"CWE-835"
],
"cna_assigner": "EEF",
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/82xxx/CVE-2026-82579.json"
}
},
"related_cves": [
{
"value": "CVE-2026-82579",
"evidence": "/id"
}
],
"security_relevant": true,
"severity_evidence": "/severity/0/score"
},
"source_id": "core-osv",
"document_id": 505277,
"published_at": "2026-08-31T01:07:49.185+00:00"
}