! Security: Review · 58 58/100 · grade D scanned 15h ago
⚠ 1 compromise signal 7 risk-surface · 6/20 OWASP controls flagged
Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface , expected for some capabilities. Every finding is mapped to its OWASP control below.
What this capability can do · low confidence (static)
⚑ secrets
egress → img.shields.io, discord.gg, www.youtube.com, platform.openai.com, www.perplexity.ai, www.anthropic.com, ai.google.dev, api.openai.com +5
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
⚠ LLM02 Sensitive Information Disclosure compromise · high Secrets, credentials or PII shipped inside the artifact.
• Embedded credentials — found: hardcoded credential · Robitx-gp.nvim-c37f154/lua/gp/dispatcher.lua (CWE-798)compromise
⚠ LLM07 System Prompt Leakage compromise · high Secrets, internal hosts or proprietary logic exposed in shipped prompts.
• Embedded credentials — found: hardcoded credential · Robitx-gp.nvim-c37f154/lua/gp/dispatcher.lua (CWE-798)compromise
⚠ LLM01 Prompt Injection high Adversarial instructions embedded in an artifact that hijack a downstream LLM.
• Trojan-source (bidi) characters — Unicode bidirectional overrides can hide code from reviewers · Robitx-gp.nvim-c37f154/README.md (CWE-1007)expected
⚠ LLM05 Improper Output Handling medium Code that pipes model/user output into shell, eval, SQL or paths unsafely.
• Path traversal sequences — '../' present in content or name · Robitx-gp.nvim-c37f154/README.md (CWE-22)risk surface
⚠ LLM06 Excessive Agency medium Over-broad tool/permission surface or unrestricted egress.
• External endpoints declared — 1 distinct host(s) · Robitx-gp.nvim-c37f154/CHANGELOG.md risk surface
• Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · Robitx-gp.nvim-c37f154/README.md (CWE-272)risk surface
• External endpoints declared — 15 distinct host(s) · Robitx-gp.nvim-c37f154/README.md risk surface
• External endpoints declared — 12 distinct host(s) · Robitx-gp.nvim-c37f154/doc/gp.nvim.txt risk surface
• External endpoints declared — 10 distinct host(s) · Robitx-gp.nvim-c37f154/lua/gp/config.lua risk surface
§ 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.
✓ LLM03 Supply Chain 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.
✓ 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
⚠ ML09 Output Integrity medium Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
• Path traversal sequences — '../' present in content or name · Robitx-gp.nvim-c37f154/README.md (CWE-22)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.
✓ 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.
✓ ML06 AI Supply Chain Passed
✓ 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 (3) · hygiene / uncategorized • Unrecognized file type — '.editorconfig' is not on the allowlist · Robitx-gp.nvim-c37f154/.editorconfig risk surface
• Unrecognized file type — '.?' is not on the allowlist · Robitx-gp.nvim-c37f154/LICENSE risk surface
• Unrecognized file type — '.lua' is not on the allowlist · Robitx-gp.nvim-c37f154/lua/gp/config.lua risk surface
✔ verified source · pinned Robitx-gp.nvim-c37f154
Check against a policy
The same gate an agent runs before installing (POST /api/v1/trust/gp-nvim/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)