CVE-2026-107293
Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when
Published Oct 8, 2026 · corrected/updated Oct 15, 2026 · evidence confidence high
### Summary Pydantic AI's OpenTelemetry instrumentation supports to exclude message content — user prompts, model completions, tool call arguments and responses — from exported telemetry, so that agents can be monitored without sending sensitive content to the observability backend. Retry prompts — the feedback messages Pydantic AI sends back to the model when its output fails validation or an output validator raises — were not covered by this setting when they were not associated with a tool call, as with structured output modes that don't use tool calls (e.g. or ) and output validators applied to text output. Their full content was recorded on model request spans even with . Since validation feedback can quote invalid values from the model's response, message content that the setting was configured to withhold could reach the telemetry backend. ### Details Retry prompts without an associated tool call were serialized into span message attributes (such as and ) as regular text parts, and this path did not apply the check that every other message part applies. Retry prompts tied to a tool call, and all other message content, were redacted correctly. ### Impact This does not grant an attacker any new access to the agent or its data: the content is only visible to whoever can read the exported telemetry. The exposure matters when traces are exported to a destination whose audience is broader or less trusted than the agent's own data — a third-party observability vendor or a shared backend — which is the scenario exists for. The disclosed content is limited to retry feedback: validation error details, which can quote invalid values from the model's output, or output-validator messages. ### Who Is Affected You are affected if you enabled instrumentation with and your agent can produce retry prompts outside of tool calls: it uses a structured output mode that doesn't rely on tool calls (such as or ), or output validators on text output. You are not affected if you don't
Grounded briefings
Catalog interpretations for three audiences. Each brief cites ingested metadata and the original advisories below. They are not independent research and they do not invent exploit steps.
Executive
CVE-2026-107293 is a low public vulnerability record for this product. It is not currently listed in the CISA Known Exploited catalog. Check the linked vendor or CERT advisories for patch status. This summary is a catalog interpretation of the ingested metadata and cites the original advisories below.
System administrator
Identify whether this product is in your estate, then compare installed versions with the affected ranges. Affected packages or ranges on record: pydantic-ai (0.3.4 → 1.107.4); pydantic-ai (2.0.0b1 → 2.27.1); pydantic-ai-slim (0.3.4 → 1.107.4); pydantic-ai-slim (2.0.0b1 → 2.27.1). Check the linked vendor or CERT advisories for patch status. Prefer the vendor or distribution advisory linked in Sources before changing production systems. This is a catalog interpretation, not a runbook.
Security analyst
Signals on file: EPSS 0.3%. It is not currently listed in the CISA Known Exploited catalog. Weakness classes: CWE-212, CWE-532. Sources contributing to this record: cve_org, epss, github, osv. Public exploit references, when present, are outbound links only and are not proof of active exploitation. This is a catalog interpretation of stored metadata.
Exploitation and remediation
Exploitation evidence
Not listed as known exploited in CISA KEV. Not in the CISA KEV catalog.
Patch and remediation
No required-action text is stored yet. Use the vendor or CERT links in Sources for patch availability.
Safe detection guidance
Compare installed versions with the affected ranges below and verify the advisory from the original publisher. This site stores metadata and outbound links only; it does not ship exploit code or proof-of-concept payloads.
Code
The project this record applies to. Exploit listings stay in References.
Timeline
Detection, updates, and resolution for this record.
Oct 8, 2026 · GitHub Advisory Database
Detected
### Summary Pydantic AI's OpenTelemetry instrumentation supports to exclude message content — user prompts, model completions, tool call arguments and responses — from exported telemetry, so that agents can be monitored without sending sensitive content to the observability backend. Retry prompts — the feedback messages Pydantic AI sends back to the model when its output fails validation or an out
Oct 15, 2026 · GitHub Advisory Database
Fix available
pydantic-ai-slim fixed in 1.107.4
Oct 15, 2026 · GitHub Advisory Database
Fix available
pydantic-ai fixed in 1.107.4; pydantic-ai fixed in 2.27.1; pydantic-ai-slim fixed in 1.107.4; pydantic-ai-slim fixed in 2.27.1
Oct 15, 2026 · GitHub Advisory Database
Fix available
pydantic-ai fixed in 1.107.4
Oct 15, 2026 · GitHub Advisory Database
Fix available
pydantic-ai fixed in 2.27.1
Oct 15, 2026 · GitHub Advisory Database
Fix available
pydantic-ai-slim fixed in 1.107.4
Oct 15, 2026 · GitHub Advisory Database
Fix available
pydantic-ai-slim fixed in 2.27.1
Oct 15, 2026 · GitHub Advisory Database
Fix available
pydantic-ai fixed in 1.107.4
Oct 15, 2026 · GitHub Advisory Database
Updated
### Summary Pydantic AI's OpenTelemetry instrumentation supports to exclude message content — user prompts, model completions, tool call arguments and responses — from exported telemetry, so that agents can be monitored without sending sensitive content to the observability backend. Retry prompts — the feedback messages Pydantic AI sends back to the model when its output fails validation or an out
Affected
- PyPI pydantic-ai0.3.4 → 1.107.4
- PyPI pydantic-ai2.0.0b1 → 2.27.1
- PyPI pydantic-ai-slim0.3.4 → 1.107.4
- PyPI pydantic-ai-slim2.0.0b1 → 2.27.1
Sources
- CVE.orgVulnerability recordCVE-2026-107293
Official CVE identifier
cve.org - FIRST EPSSExploitation probabilityCVE-2026-107293
30-day exploitation probability 0.3%
first.org - GitHub Advisory DatabasePackage advisoryGHSA-3gh4-cghq-f8v4
GitHub Advisory Database record mirrored by OSV.
github.com - OSV.devPackage advisoryGHSA-3gh4-cghq-f8v4
Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when
osv.dev - OSV.devPackage advisoryPYSEC-2026-4274
Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when
osv.dev - OSV.devPackage advisoryPYSEC-2026-4283
Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when
osv.dev