Home/VLMEvalKit/Trust report

Trust and health report

VLMEvalKit - trust report

Sourced, dated trust signals - maintenance label posture, repository provenance, and security scan status. Not a composite safety grade.

GraphCanon updated 4d · GitHub synced 4d

Maintenance

Recency and activity heuristics from public GitHub metadata (maintenance label, momentum); methodology: github_public_v1.

Very active96% signal

last push 0d ago · last release 1y

+60 stars (30d) · +21 open issues (30d)

Provenance

Repository identity and fork provenance (github_public_v1).

Security intelligence

Source-by-source security scan results from public intelligence providers. Missing, partial, or failed queries are shown explicitly and are not treated as clean.

OSV dependency advisories

Published findings
Last query
1mo
Scanner
osv@v1
Stored findings
16
View source evidence

deps.dev advisories

Not queried
Scanner
deps.dev@v1
View source evidence

OpenSSF Scorecard

Not queried
Scanner
openssf-scorecard@v1

Weekly public scans omit some checks at scale.

View source evidence

Dependency advisories (deduplicated)

GHSA-4xpc-pv4p-pm3w
litellm@1.55 · osv@v1
requirements.txt
GHSA-53mr-6c8q-9789
litellm@1.55 · osv@v1
requirements.txt
GHSA-69x8-hrgq-fjj8
litellm@1.55 · osv@v1
requirements.txt
GHSA-fh2c-86xm-pm2x
litellm@1.55 · osv@v1
requirements.txt
GHSA-fjcf-3j3r-78rp
litellm@1.55 · osv@v1
requirements.txt
GHSA-jjhc-v7c2-5hh6
litellm@1.55 · osv@v1
requirements.txt
GHSA-qrc4-49gv-mv9m
litellm@1.55 · osv@v1
requirements.txt
GHSA-wpfp-gwwc-vwq6
litellm@1.55 · osv@v1
requirements.txt
PYSEC-2026-1545
litellm@1.55 · osv@v1
requirements.txt
PYSEC-2026-1546
litellm@1.55 · osv@v1
requirements.txt
PYSEC-2026-388
litellm@1.55 · osv@v1
requirements.txt
PYSEC-2026-390
litellm@1.55 · osv@v1
requirements.txt
GHSA-vfmq-68hx-4jfw
lxml@6.0.2 · osv@v1
requirements.txt
PYSEC-2026-87
lxml@6.0.2 · osv@v1
requirements.txt
GHSA-qr4w-53vh-m672
opencv-python@4.7.0.72 · osv@v1
requirements.txt
PYSEC-2023-183
opencv-python@4.7.0.72 · osv@v1
requirements.txt

Method and caveats: these are sourced, dated heuristics from public GitHub data and external security intelligence providers. A status like "no published findings from this source" is not a guarantee of safety. Read the full trust methodology · JSON report at /api/graphcanon/tools/open-compass-vlmevalkit/trust.

Common questions

Is VLMEvalKit maintained?
GraphCanon rates VLMEvalKit "Very active" (96% maintenance signal from public GitHub metadata, computed 4d). Last push was 0 days ago. This is a recency heuristic, not a guarantee the project will stay maintained.
Is VLMEvalKit safe to use?
Last scanned 1mo (deps profile). Status: 16 low - 16 low finding(s) in the latest scan. GraphCanon does not claim the project is safe or vulnerability-free; review findings on the trust report. GraphCanon does not certify VLMEvalKit as safe - review maintenance, provenance, and scan findings on this page before adopting.
Is VLMEvalKit a fork?
No. VLMEvalKit is not flagged as a fork in GitHub metadata at the time of the last refresh.
Does VLMEvalKit have known security vulnerabilities?
Last scanned 1mo (deps profile). Status: 16 low - 16 low finding(s) in the latest scan. GraphCanon does not claim the project is safe or vulnerability-free; review findings on the trust report.
How often is the VLMEvalKit trust report updated?
Trust signals refresh on GitHub ingest/refresh cycles and optional dependency/MCP scans. This report was computed 4d (methodology github_public_v1).
What does GraphCanon never claim about VLMEvalKit?
We never publish a composite safety grade, pen-test endorsement, or "verified secure" label for VLMEvalKit. Signals are sourced heuristics with explicit limits - see trust methodology.
How does GraphCanon assess trust for VLMEvalKit?
Signals are sourced from public GitHub metadata and optional dependency/MCP manifest scans, each tagged with methodology version and computed date. GraphCanon does not publish a composite safety grade. Read trust methodology for full scope and limits.

Was this helpful?

Anonymous feedback helps us improve pages and translations.