# CVE-2026-82564: ash-project ash_ai authorization bypass in identity-configured tools

Source: https://junglewise.ai/threats/cve-2026-82564-ash-project-ash-ai-authorization-bypass-in-identity-configured  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-08-31. Updated: 2026-09-25  
License: CC BY 4.0 with a link back

CVE-2026-82564 · Severity: info · CVSS 7.5 · Published 2026-08-31

AshAI is a library that provides AI-powered tool execution capabilities. A vulnerability in how it validates user identity allows an attacker with access to an identity-configured tool to modify or delete database records they should not have permission to access, potentially affecting entire tables of data.

Technologies: [Ash-Project Ash Ai](https://junglewise.ai/threats/technologies/ash-ai). Vendors: [Ash-Project](https://junglewise.ai/threats/vendors/ash-project).

## Quick answers

**Is CVE-2026-82564 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-82564 being exploited in the wild.

**How severe is CVE-2026-82564?** Informational severity, with a CVSS score of 7.5, published 31 August 2026.

**Which products and versions are affected?** Ash-Project Ash Ai 0.6.0 before 1.0.0.

**Is there a fix for CVE-2026-82564?** No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.

**How is CVE-2026-82564 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-82564?** Check whether you run Ash-Project Ash Ai at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## Technical details

The vulnerability is an authorization bypass in AshAi.Tool.Execution's identity_filter/3 function, which constructs database filters from raw tool arguments without proper validation. Map values in filter arguments are interpreted as predicate expressions rather than literal values, allowing attackers to inject operators like "not_eq" to retarget updates or deletes at unintended records. Combined with Ash.Query.limit(1) and bulk write operations, an attacker can modify or destroy rows they never identified. The fix casts identity values to their field type and rejects non-scalar inputs. The vulnerability affects versions 0.6.0 through 1.0.0 (exclusive) and requires network access to a tool endpoint.

## Affected products

- ash-project ash_ai 0.6.0 before 1.0.0

## Timeline

- 2026-08-31: disclosed

## References

- [https://repo.hex.pm/](https://repo.hex.pm/)
- [https://github.com/](https://github.com/)

## Related threats

- [ash-project ash_ai sensitive information disclosure in error messages](https://junglewise.ai/threats/cve-2026-119613-generation-of-error-message-containing-sensitive-information)
- [ash-project ash_ai information disclosure in error messages](https://junglewise.ai/threats/cve-2026-82580-ash-project-ash-ai-information-disclosure-in-error-messages)
- [Ash AI tool loop infinite loop via prompt injection](https://junglewise.ai/threats/cve-2026-82579-ash-ai-tool-loop-infinite-loop-via-prompt-injection)
- [ash-project ash_ai sensitive information disclosure in error messages](https://junglewise.ai/threats/cve-2026-75760-ash-project-ash-ai-sensitive-information-disclosure-in-error)
- [ash-project ash_ai origin validation bypass in MCP server](https://junglewise.ai/threats/cve-2026-81315-ash-project-ash-ai-origin-validation-bypass-in-mcp-server)