GHSA-WVP9-4G4G-QWGM
Vulnerability from github – Published: 2026-11-19 15:31 – Updated: 2026-11-19 15:31Summary ui
With strip_ansi=True, Pydantic AI Harness's ToolOutputLimits capability removes ANSI escape sequences from tool output with a pattern that takes time quadratic in the length of a line. A tool result of a few hundred kilobytes, crafted with many unterminated escape sequences, can occupy the event loop for tens of seconds to minutes, delaying every other request and agent run in the process.
Details
This affects applications that set strip_ansi=True on ToolOutputLimits (named OverflowingToolOutput before 0.13.0) and run tools whose output an attacker can influence, such as shell commands, file reads, fetched pages or MCP servers. Stripping runs on the event loop before the capability reduces the output, so its own size limits do not bound it.
The assumed attacker can place text in content a tool returns.
Mitigation
Upgrade pydantic-ai-harness to 0.70.0 or later. Until then, leave strip_ansi at its default, False.
On Pydantic AI v1, the harness cannot be upgraded past 0.4.0. Upgrade to Pydantic AI v2 and pydantic-ai-harness 0.70.0, or leave strip_ansi off.
{
"affected": [],
"aliases": [
"CVE-2026-133161"
],
"database_specific": {
"cwe_ids": [
"CWE-1333"
],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2026-11-19T15:17:35Z",
"severity": "HIGH"
},
"details": "### Summary ui\n\nWith `strip_ansi=True`, Pydantic AI Harness\u0027s `ToolOutputLimits` capability removes ANSI escape sequences from tool output with a pattern that takes time quadratic in the length of a line. A tool result of a few hundred kilobytes, crafted with many unterminated escape sequences, can occupy the event loop for tens of seconds to minutes, delaying every other request and agent run in the process.\n\n### Details\n\nThis affects applications that set `strip_ansi=True` on `ToolOutputLimits` (named `OverflowingToolOutput` before 0.13.0) and run tools whose output an attacker can influence, such as shell commands, file reads, fetched pages or MCP servers. Stripping runs on the event loop before the capability reduces the output, so its own size limits do not bound it.\n\nThe assumed attacker can place text in content a tool returns.\n\n### Mitigation\n\nUpgrade `pydantic-ai-harness` to 0.70.0 or later. Until then, leave `strip_ansi` at its default, `False`.\n\nOn Pydantic AI v1, the harness cannot be upgraded past 0.4.0. Upgrade to Pydantic AI v2 and `pydantic-ai-harness` 0.70.0, or leave `strip_ansi` off.",
"id": "GHSA-wvp9-4g4g-qwgm",
"modified": "2026-11-19T15:31:15Z",
"published": "2026-11-19T15:31:15Z",
"references": [
{
"type": "WEB",
"url": "https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-m4cr-m4qc-9hh3"
},
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-133161"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H",
"type": "CVSS_V3"
}
]
}
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.