Who it is for
No explicit purpose, audience or use case was extracted from the inspected README.
PUBLIC REPORT / AGENT SIGNAL v0.2
pydantic-ai.
Automated source and domain checks for pydantic/pydantic-ai.
Inspect GitHub source0community interest
Votes show community interest, not safety. They never change this score.
70/100BBBNot security certification
Critical findings need attention.
Critical finding · details withheld for 30 days
Inspect the findingsRuntime safety, real-world agent capability, fitness for your use case or independent certification.
Scan scope200 / 916Partial eligible-file selection · not the entire repository
Recorded findings11Heuristic matches requiring human review
SnapshotOct 11, 2026UTC · engine 0.4.0
DNS at scan timeUnverifiedDomain control is not security certification
What the source
actually tells us.
Structured, cited information from the scanned archive. Repository-authored claims are labeled and never treated as verified capabilities.
200 / 916Partial selection
ReadRepository-authored information
1LICENSE
What it can do
No explicit capability or integration was extracted; that does not mean none exists.
What adoption takes
No matching setup or dependency statement was extracted from inspected metadata.
Limits and terms
A license or copying file is present; its terms have not been reviewed.
LICENSE:1
Observed technical context
Python · 200 selected filesTool-calling reference · static only
These are references in selected source files, not proof that a feature works at runtime.
Read from commit 69ea1e5 at Oct 11, 2026, 10:32 AM UTC. Source links open that exact commit. Repository statements are unreviewed and do not affect the score.
02 / FINDINGS FIRSTWhat needs
What needs
a closer look.
Critical details are withheld publicly for the first 30 days after a scan. A matched pattern is a lead for investigation, not a confirmed vulnerability.
Dependencies: 381 exact runtime versions from uv.lock checked against OSV.dev on Oct 11, 2026; 11 with known advisories. Reachability is not checked.
11 findings
CRITICALCritical finding · details withheld for 30 days
Critical finding · details withheld for 30 days
Details are withheld from public view for 30 days after the scan. The owner can see them in full.
Review the private assessment and address the finding.
CRITICALCritical finding · details withheld for 30 days
Critical finding · details withheld for 30 days
Details are withheld from public view for 30 days after the scan. The owner can see them in full.
Review the private assessment and address the finding.
MAJORDomain ownership not verified
Domain ownership not verified
Metal Mantra could not confirm that the owner controls the stated domain. The domain may belong to someone else.
Verify the domain using the Metal Mantra DNS TXT challenge.
MAJORDependency with a high-severity advisory
Dependency with a high-severity advisory
sentence-transformers 5.2.2 (PyPI) has known advisories: GHSA-jhr6-gm9c-rqjv, PYSEC-2026-4164 (highest severity critical). sentence-transformers local model loading bypasses trust_remote_code and executes custom Python
Upgrade to a fixed version listed in the advisory and regenerate the lockfile.
MAJORDependency with a high-severity advisory
Dependency with a high-severity advisory
cryptography 49.0.0 (PyPI) has known advisories: GHSA-g6cj-pr64-35w5, PYSEC-2026-3552 (highest severity high). cryptography: PKCS#7 EnvelopedData decryption exposes a Bleichenbacher oracle through distinguishable errors and timing
Upgrade to a fixed version listed in the advisory and regenerate the lockfile.
MAJORDependency with a high-severity advisory
Dependency with a high-severity advisory
fsspec 2025.10.0 (PyPI) has a known advisory: GHSA-27vj-qcqg-25rc (highest severity high). fsspec: Server-Side Template Injection in ReferenceFileSystem leads to Remote Code Execution
Upgrade to a fixed version listed in the advisory and regenerate the lockfile.
MINORRaw model text returned
Raw model text returned
The code returns the model's raw text. Output that was never parsed or validated can pass mistakes straight to users or other systems.
Parse and validate the result before returning it.
MINORRaw model text returned
Raw model text returned
The code returns the model's raw text. Output that was never parsed or validated can pass mistakes straight to users or other systems.
Parse and validate the result before returning it.
MINORDependency with a known advisory
Dependency with a known advisory
datasets 4.4.2 (PyPI) has known advisories: GHSA-379c-qx7v-6h59, PYSEC-2026-3716 (highest severity moderate). Hugging Face Datasets folder-based builders allow path traversal through file_name metadata
Upgrade to a fixed version listed in the advisory and regenerate the lockfile.
MINORDependency with a known advisory
Dependency with a known advisory
mako 1.3.12 (PyPI) has a known advisory: GHSA-5639-2j2p-m4mx (highest severity moderate). Mako: Path traversal via drive-letter URI on Windows in TemplateLookup
Upgrade to a fixed version listed in the advisory and regenerate the lockfile.
MINORDependency with a known advisory
Dependency with a known advisory
multidict 6.7.0 (PyPI) has a known advisory: GHSA-54p9-h82j-f925 (highest severity moderate). Multidict: Reference leak in CIMultiDict/MultiDict items-view union and subtraction
Upgrade to a fixed version listed in the advisory and regenerate the lockfile.
The boundary
is part of the result.
- What was scanned
- 200 of 916 eligible files · Partial selection.
Supported static source patterns and domain checks; no runtime execution. - What remains unknown
- Unscanned files, external dependencies, production configuration, actual agent behavior and evidence beyond the configured checks.
- Source location
- Links open the current repository HEAD. Source may have changed since this snapshot.
- Something looks wrong?
- Tell us if a finding, scope or claim on this report needs a correction. Report a problem with this report
- Entity trust · 15% of v0.2
- Includes DNS ownership, HTTPS and policy evidence. Verification is domain control, not a security certificate.DNS: unverifiedHTTPS: availablePrivacy: foundTerms: found
Open the
calculation.
Each pillar starts at 100. Rule deductions reduce its score; weights determine the overall contribution.
Security & privacy
22/100
Guardrails & loop control
100/100
Schema & tooling
84/100
Token & cost efficiency
100/100
Entity trust
50/100
Did pydantic-ai work for people?
No user reports yet.
Each report is one signed-in GitHub account saying what happened. We do not verify that the account ran the agent, and reports never change the automated score or grade. For a security problem, use the disclosure page instead of a public note.
SHARE THE EVIDENCEA signal.
A signal.
Not a seal.
Share the full report so its scope and limits travel with the score.
