✓ Security: Safe · 100 100/100 · grade A scanned 35m ago
✓ no compromise signals 7 risk-surface · 3/20 OWASP controls flagged
Only compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score. Dangerous-by-capability traits are risk surface , expected for some capabilities. Every finding is mapped to the OWASP control it belongs to below.
What this capability can do · low confidence (static)
egress → help.github.com, smithery.ai, modelcontextprotocol.io, qdrant.tech, docs.astral.sh, xyz-example.eu-central.aws.cloud.qdrant.io, qdrant.github.io, docs.cursor.com +4
Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10 . Expand any flagged control for the exact findings — compromise reduces the score; expected /risk-surface do not.
OWASP Top 10 for LLM Applications
⚠ LLM03 Supply Chain critical Vulnerable/compromised dependencies, models or archives in the artifact.
• Vulnerable dependencies — 77 known vulnerabilities in: authlib@1.6.5, cryptography@46.0.3, fastmcp@2.7.0, filelock@3.20.0, idna@3.11, pillow@11.3.0, protobuf@6.33.1, pydantic-settings@2.12.0 (CWE-1395)risk surface
⚠ LLM06 Excessive Agency medium Over-broad tool/permission surface or unrestricted egress.
• External endpoints declared — 1 distinct host(s) · qdrant-mcp-server-qdrant-f1a4d04/.github/workflows/pypi-publish.yaml expected
• External endpoints declared — 3 distinct host(s) · qdrant-mcp-server-qdrant-f1a4d04/.gitignore expected
• Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · qdrant-mcp-server-qdrant-f1a4d04/README.md (CWE-272)risk surface
• External endpoints declared — 13 distinct host(s) · qdrant-mcp-server-qdrant-f1a4d04/README.md expected
• External endpoints declared — 2 distinct host(s) · qdrant-mcp-server-qdrant-f1a4d04/tests/test_settings.py expected
§ LLM09 Misinformation Governance Artifacts designed to produce false/deceptive output.
Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.
◷ LLM10 Unbounded Consumption Runtime-enforced Unbounded loops/recursion causing DoS or runaway cost.
Enforced at runtime by the gateway (rate limits + spend caps + size caps); static check flags unbounded loops.
✓ LLM01 Prompt Injection Passed
✓ LLM02 Sensitive Information Disclosure Passed
✓ LLM04 Data and Model Poisoning Passed Backdoors/poisoning in training data or serialized models.
Behavioral poisoning needs model execution; static check covers unsafe serialization + dataset skew only.
✓ LLM05 Improper Output Handling Passed
✓ LLM07 System Prompt Leakage Passed
✓ LLM08 Vector and Embedding Weaknesses Passed PII or plaintext source leakage in embedding/vector exports.
Embedding inversion/poisoning is largely runtime; static check covers PII in vector exports.
OWASP Machine Learning Security Top 10
⚠ ML06 AI Supply Chain critical Compromised PyPI/npm packages, typosquats, unsafe serialized models.
• Vulnerable dependencies — 77 known vulnerabilities in: authlib@1.6.5, cryptography@46.0.3, fastmcp@2.7.0, filelock@3.20.0, idna@3.11, pillow@11.3.0, protobuf@6.33.1, pydantic-settings@2.12.0 (CWE-1395)risk surface
§ ML01 Input Manipulation (Adversarial) Governance Models vulnerable to adversarial perturbations.
Requires runtime robustness evaluation; addressed via publisher robustness attestation.
§ ML03 Model Inversion Governance Training data reconstructable from a model's outputs.
Runtime/evaluation property; addressed via model-card data-provenance + DP attestation.
§ ML04 Membership Inference Governance Determining whether a record was in the training set.
Runtime/evaluation property; addressed via overfitting disclosure + DP attestation.
§ ML08 Model Skewing Governance Models trained on skewed data producing biased output.
Requires fairness evaluation; addressed via model-card bias/limitations disclosure.
◷ ML09 Output Integrity Runtime-enforced Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
✓ ML02 Data Poisoning Passed Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
✓ ML05 Model Theft Passed Unlicensed re-distribution / license-incompatible derivatives.
Static check verifies license declaration; extraction throttling is runtime.
✓ ML07 Transfer Learning Attack Passed Backdoored base models / LoRA adapters propagating to derivatives.
Backdoor detection needs behavioral probing; static check covers unsafe serialization + provenance.
✓ ML10 Model Poisoning (Weights) Passed Tampered model weight files; integrity must be verifiable.
Static check enforces safe formats + records a content hash for downstream verification.
Other findings (4) · hygiene / uncategorized • Unrecognized file type — '.gitignore' is not on the allowlist · qdrant-mcp-server-qdrant-f1a4d04/.gitignore risk surface
• Unrecognized file type — '.python-version' is not on the allowlist · qdrant-mcp-server-qdrant-f1a4d04/.python-version risk surface
• Unrecognized file type — '.?' is not on the allowlist · qdrant-mcp-server-qdrant-f1a4d04/Dockerfile risk surface
• Possible obfuscation — very long lines · qdrant-mcp-server-qdrant-f1a4d04/README.md risk surface
✔ verified source · pinned qdrant-mcp-server-qdrant-f1a4d04 · changed since last scan · +egress help.github.com, smithery.ai, modelcontextprotocol.io, qdrant.tech, docs.astral.sh, xyz-example.eu-central.aws.cloud.qdrant.io, qdrant.github.io, docs.cursor.com, code.visualstudio.com, img.shields.io, insiders.vscode.dev
Check against a policy
The same gate an agent runs before installing (POST /api/v1/trust/qdrant-mcp-server/check). Click a policy:
No shell/exec No unknown egress Grade B or better No secrets access No install hooks Strict (B+ · no shell · no egress)