EEF-CVE-2026-82579 CVE-2026-82579 GHSA-rcx7-x2w5-mmc2
AshAi tool loop never terminates when all tool calls are filtered out, enabling denial of service
- Severity
- 0.0 / 10
- Unknown · CVSS 4.0
- Exploit chance (EPSS)
- 0.47%
- Chance of exploitation in the next 30 days. Higher than 40.35% of scored vulnerabilities.
- Known exploited
- No
- Not in CISA's catalog
- Weakness
- CWE-835 Loop with Unreachable Exit Condition ('Infinite Loop')
- Fix
1.0.0- Upgrade ash_ai to this version or later
Description
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.
Affected versions
Hex
| Package | Vulnerable | Fixed in |
|---|---|---|
| ash_ai | >= 0.6.0, < 1.0.0 |
1.0.0 |
How to fix
Move to the fixed version or later with your package manager, update the lockfile, and run your tests. If the package only arrives through another dependency, upgrade that dependency first. If none of its releases pulls a fixed version yet, force the version with your package manager's override.
ash_ai Hex → 1.0.0
- mix
{:ash_ai, "~> 1.0.0"} # then: mix deps.update ash_ai
Severity breakdown
CVSS 4.0 0.0
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
- Attack vector
- Network
- Attack complexity
- Low
- Attack requirements
- Present
- Privileges required
- Low
- User interaction
- None
- Confidentiality (vulnerable system)
- None
- Integrity (vulnerable system)
- None
- Availability (vulnerable system)
- High
- Confidentiality (subsequent systems)
- None
- Integrity (subsequent systems)
- None
- Availability (subsequent systems)
- None
Weakness
CWE-835: Loop with Unreachable Exit Condition ('Infinite Loop')
The product contains an iteration or loop with an exit condition that cannot be reached, i.e., an infinite loop.
References
Advisories
Fixes and patches
Packages
Other links
Timeline
- Published
- Last updated by the source
- Latest EPSS score
Related advisories
| Advisory | Severity | Why it's related |
|---|---|---|
| EEF-CVE-2026-78230 AshAi aggregate tool can read field-policy-protected fields | Not rated yet | Also affects ash_ai |
| EEF-CVE-2026-75760 AshAi vectorize change leaks raw embedding-provider errors, including credentials, in a user-facing error | Not rated yet | Also affects ash_ai |
| EEF-CVE-2026-82580 AshAi echoes raw tool exception messages into the conversation, disclosing internal details | Not rated yet | Also affects ash_ai |
| EEF-CVE-2026-82564 Identity tool filter in AshAi accepts operator maps, allowing update or destroy of unidentified records | Not rated yet | Also affects ash_ai |
| EEF-CVE-2026-81315 MCP DNS-rebinding origin check in AshAi is bypassed by a spoofed X-Forwarded-Proto header | Not rated yet | Also affects ash_ai |
| EEF-CVE-2026-77956 EEx template evaluation of prompt content in AshAi enables remote code execution | Not rated yet | Also affects ash_ai |
| GHSA-5849-834g-hvw5 pypdf has possible infinite loop when hitting EOF in standard xref table during trailer search | High | Same weakness, CWE-835 |
| GHSA-mfr5-77xh-9j7h pypdf has possible infinite loop when cloning dictionaries | High | Same weakness, CWE-835 |
Credits: Jonatan Männchen / EEF, Peter Ullrich, Zach Daniel / Ash Project
MergeHarbor checks every repository's dependencies against this database, ranks what matters by exploitability and reachability, routes it to the owning team and opens the fix pull request.
Check your repos with MergeHarbor