ETK-2026-3502Zero's internal tracking ID, independent of the CVE number.

waiting for further signalsZero needs more public information before it can validate it.

GHSA-m5vj-8mcw-82qx ↗

no check availablenot proven exploitable
awaiting cvepublic pocExploit code has been published by someone. Source signals can also carry a PoC (Proof of Concept).kevAttacks confirmed in the real world.
pip:pydantic-ai >= 1.77.0, <= 1.107.9; >= 2.0.0b1, <= 2.65.0
fixed in 1.107.10, 2.66.0
CWE-400 Uncontrolled Resource Consumption
ETK-2026-3502Zero's internal tracking ID, independent of the CVE number., no cve assigned
pkg:pypi/pydantic-ai
pkg:pypi/pydantic-ai-slim
2h 41msince last run
13mAI analysisAnalysis: how long the AI spent reversing this signal.
timeline
0 = trigger signal
trigger signal +0hwaiting for further signals+1h31m
0
+1h
+2h
+3h
+4h

description

Pydantic AI local web fetching can consume excessive memory and block other work while processing specially structured JSON responses. Applications are affected when they use web_fetch_tool or the local WebFetch fallback and an attacker can influence a fetched URL; provider-native fetching is not affected.

mitigation

Upgrade pydantic-ai or pydantic-ai-slim to 1.107.10 or 2.66.0, as appropriate for the deployed release line. Until upgraded, limit local web fetching with allowed_domains to trusted hosts or use provider-native web fetching.

fixed in 1.107.10, 2.66.0

check
no
exploit
no
automationDeterministic: a check that runs on its own, the same request on every target. Contextual: an agentic technique that needs to be applied per target, for bugs that depend on contextual flows.
contextual
auth requiredWhether an attacker needs an account first, based on the CVSS vector's Privileges Required.
no
EPSSEstimate of the chance this CVE is exploited in the next 30 days. Refreshed daily.
–
agent run time
13m
cve.org record, t = 0The moment cve.org publishes the CVE in full.
not published yet
Δ to public pocExploit code has been published by someone. Source signals can also carry a PoC (Proof of Concept).
–
Δ to kevAttacks confirmed in the real world.
–

outcome

Contextual, not validated: no deterministic check could cover this one, and no technique passed our review.

source signals

Public signals that triggered or updated the pipeline. These are inputs for the deltas above.

  1. 2026-11-04 11:51Z

this entry in the feed

GET /api/v1/feed/ETK-2026-3502

{
  "etk_id": "ETK-2026-3502",
  "cve_id": null,
  "display_id": "ETK-2026-3502",
  "ghsa_id": "GHSA-m5vj-8mcw-82qx",
  "euvd_id": null,
  "status": "published",
  "anchor_state": "awaiting_cve",
  "title": "JSON formatting resource exhaustion in Pydantic AI web fetching",
  "summary": "Pydantic AI local web fetching can consume excessive memory and block other work while processing specially structured JSON responses. Applications are affected when they use web_fetch_tool or the local WebFetch fallback and an attacker can influence a fetched URL; provider-native fetching is not affected.",
  "mitigation": "Upgrade pydantic-ai or pydantic-ai-slim to 1.107.10 or 2.66.0, as appropriate for the deployed release line. Until upgraded, limit local web fetching with allowed_domains to trusted hosts or use provider-native web fetching.",
  "vendor": "pip",
  "product": "pip:pydantic-ai",
  "affected": [
    {
      "affected_notes": [],
      "affected_ranges": [
        ">= 1.77.0, <= 1.107.9"
      ],
      "ecosystem": "pip",
      "fixed_versions": [
        "1.107.10"
      ],
      "package_name": "pydantic-ai",
      "purl": "pkg:pypi/pydantic-ai"
    },
    {
      "affected_notes": [],
      "affected_ranges": [
        ">= 2.0.0b1, <= 2.65.0"
      ],
      "ecosystem": "pip",
      "fixed_versions": [
        "2.66.0"
      ],
      "package_name": "pydantic-ai",
      "purl": "pkg:pypi/pydantic-ai"
    },
    {
      "affected_notes": [],
      "affected_ranges": [
        ">= 1.77.0, <= 1.107.9"
      ],
      "ecosystem": "pip",
      "fixed_versions": [
        "1.107.10"
      ],
      "package_name": "pydantic-ai-slim",
      "purl": "pkg:pypi/pydantic-ai-slim"
    },
    {
      "affected_notes": [],
      "affected_ranges": [
        ">= 2.0.0b1, <= 2.65.0"
      ],
      "ecosystem": "pip",
      "fixed_versions": [
        "2.66.0"
      ],
      "package_name": "pydantic-ai-slim",
      "purl": "pkg:pypi/pydantic-ai-slim"
    }
  ],
  "cwes": [
    400
  ],
  "cvss_score": 7.5,
  "cvss_src": "cna_vendor",
  "cvss_vector": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H",
  "epss_score": null,
  "epss_percentile": null,
  "epss_asof": null,
  "automation": "contextual",
  "check": false,
  "check_confidence_basis": null,
  "exploit": false,
  "pipeline_minutes": 13.049183483333334,
  "t0_at": null,
  "signals": {
    "trigger_signal": {
      "at": "2026-11-04T11:51:35+00:00",
      "days": -0.17468630549768518,
      "is_lower_bound": true,
      "measured_at": "2026-11-04T16:03:07.934234+00:00",
      "url": "https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-m5vj-8mcw-82qx"
    }
  }
}

published 2026-11-04 13:25Z
last change 2026-11-04 15:49Z

Need the technical details behind an entry?

Every entry here shows what we attempted and when. The technical details, the generated exploit that fired it and the evidence behind the verdict are not public. Tell us about your use case and we’ll get back to you about extended API access.