cve.bz

CVE-2026-82580 AshAi echoes raw tool exception messages into the conversation, disclosing internal details

5.3 mediumEPSS 0.3%Fix available

Medium (5.3) in ash-project ash ai. EPSS 0.3% estimated probability of exploitation activity in the next 30 days. Fixed in ash_ai 1.0.0.

On this page
Generation of Error Message Containing Sensitive Information vulnerability in ash-project ash_ai discloses internal error text to chat users. In AshAi.ToolLoop and AshAi.Tools, an exception raised while executing a tool was serialized verbatim with Exception.message/1 into the tool-result content. That content is appended to the conversation, emitted as a {:tool_result, ...} stream event, and sent back to the model, which typically relays it to the user. No filtering happened first, so anything raised inside a tool callback or lifecycle hook (database constraint messages, adapter errors, query fragments, policy or validation internals) was echoed as-is. A chat user who can steer tool arguments into a raising code path receives the raw internal text. The fix routes raised tool errors through the same safe formatter used for other tool errors. This issue affects ash_ai: from 0.6.0 before 1.0.0.

Severity

CVSS 4.0

5.3 medium
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:N/VA:N/SC:N/SI:N/SA:N
EPSS
0.3% (down from 0.5% a week ago; 0.5% 30 days ago) estimated probability of exploitation activity in the next 30 days; 28th percentile. Scored 2026-11-22. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: PoC · Automatable: no · Technical impact: partial, assessed 2026-08-31. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWE
CWE-209 Generation of Error Message Containing Sensitive Information
OWASP Top 10
A10:2025 Mishandling of Exceptional Conditions
Published
Modified
Assigned by
EEF (CNA)
NVD analysis
Deferred: the NVD does not plan to analyze it
Record from
the NVD, synced

Fix and patched versions

  • ash_ai (Hex): fixed in 1.0.0

Ask an AI about this CVE

Show the promptExplain CVE-2026-82580 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-82580?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-82580?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-82580 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.

Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.

Affected

Versions

From the CNA's record in the CVE List.

ProductAffected
ash-project ash_aifrom 0.6.0 before 1.0.0

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
EEF-CVE-2026-82580Hexash_ai>=0.6.0 <1.0.01.0.0
EEF-CVE-2026-82580v0.8.2, v0.8.1, v0.8.0, v0.7.3, v0.7.2 and 4 moreno fix published

Attack patterns (CAPEC)

  • CAPEC-7 Blind SQL Injection Likelihood: High · Severity: High
  • CAPEC-54 Query System for Information Likelihood: High · Severity: Low
  • CAPEC-215 Fuzzing for application mapping Likelihood: High · Severity: Low
  • CAPEC-463 Padding Oracle Crypto Attack Severity: High

The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits.

References

Check your stackJSON