Loading the registry…
A multi-view data system for serving repository context to coding agents
The publisher performed an authenticated act of publication — proving control of a namespace in the official MCP registry, or appearing in a first-party catalogue an operator curates. That establishes WHO published it. It is not a security finding, and attested artifacts carry Flagged verdicts too.
143 critical findings reported by cisco-skill-scanner, agent-audit-kit, 5 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
github: https://github.com/sysevol-ai/CodeNib, 388 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- codenib
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
6 of 11 scanners examined this package. The rest do not apply to it — language, ecosystem and packaging decide which analyzers can say anything, and a scanner that cannot examine an artifact reports nothing rather than passing it.
v1.4.0
2 findings · 0.6s
v2.0.11
215 findings · 38.4s
v0.3.26
167 findings · 52.9s
v0.1.0
1 finding · 41.4s
v0.1.0
3 findings · 41.4s
vv0.3.2
Incomplete run
0 findings · 0.4s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image, nerlo-multi-source.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 9, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·!: incomplete | rejected |
Findings in files this artifact installs stand as reported; a model re-read the rest and said which ones it believes are false positives. This is a second opinion published beside the evidence, not a correction to it: the per-scanner reports above are unchanged, every dismissed finding is still listed there at its original severity, and the score and the Flagged badge are computed from those raw severities alone. Nothing below moved them.
Out of 388 findings across every scanner that examined this package. 138 of 143 findings rated critical by their scanner were among the dismissals.
Two keys had to turn. The model had to name a reason from a fixed list of six, and a deterministic check of ours — over which files this artifact actually installs — had to independently agree. Anything it could not corroborate is in “not reviewed” above, at full severity.
130 Agent instruction file — The match is in a file that instructs an AI coding agent — a CLAUDE.md or similar. It is documentation of intent, and our own check confirmed it is not part of what gets installed.
Rules: AAK-AGENT-001, TOOL_ABUSE_UNDECLARED_NETWORK · Files: AGENTS.md, .claude/CLAUDE.md, /repo/repo/AGENTS.md and 1 more · reported by agent-audit-kit, cisco-skill-scanner
50 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-INDIA-PII-001, AAK-HEALTHCARE-AI-004, FILE_MAGIC_MISMATCH and 3 more · Files: docs/experiments/agent_compile_runs/sample/phase2_metrics.json, docs/diagnose_query_leak.md, docs/running-locally.md and 24 more · reported by agent-audit-kit, cisco-skill-scanner
48 Test or fixture file — The match is in a test or fixture. Our own check confirmed the file is not part of what gets installed.
Rules: COMMAND_INJECTION_EVAL, YARA_script_injection_generic, AAK-STDIO-001 and 8 more · Files: /repo/test/index/test_reranker_model_loading.py, /repo/test/serving/test_hf_engine.py, /repo/test/agent/test_query_e2e.py and 16 more · reported by cisco-skill-scanner, agent-audit-kit
5 CI or editor configuration — The match is in build, CI or editor configuration, confirmed by our own check to be outside the installed artifact.
Rules: AAK-SECRET-004, MANIFEST_INVALID_NAME · Files: test/actions/test_publish_action.py, .github/actions/publish/action.yml, .github/actions/prewarm-parsers/action.yml and 1 more · reported by agent-audit-kit, cisco-skill-scanner
These findings are in files this artifact installs and are not placeholder values. No false-positive basis can be corroborated for such a finding, so this review never dismisses one; they were not sent to the model and stand at their scanner's severity.
32 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/.codex/SKILL.md, /repo/.claude/SKILL.md and 29 more · reported by cisco-skill-scanner
32 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/.codex/SKILL.md, /repo/.claude/SKILL.md and 29 more · reported by cisco-skill-scanner
17 MANIFEST_INVALID_NAME
Files: /repo/.codex/SKILL.md, /repo/codenib/agent/skills/codenib_context/SKILL.md, /repo/codenib/agent/skills/llm_rerank/SKILL.md and 14 more · reported by cisco-skill-scanner
14 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/codenib/artifacts/github.py, /repo/codenib/web/launcher.py, /repo/scripts/smoke_release_agent.py and 3 more · reported by cisco-skill-scanner
12 DATA_EXFIL_JS_NETWORK
Files: /repo/scripts/guardian/deepswe/dashboard/app.js, /repo/web/lib/api.ts · reported by cisco-skill-scanner
Critical risks: shell execution, path traversal, and credential exposure.
The artifact contains critical command injection vulnerabilities in multiple `codenib` files, allowing shell execution. A critical path traversal vulnerability in `/repo/scripts/build_commit_window.py` permits access to arbitrary file system locations. Additionally, high-severity findings indicate potential credential exposure across several `codenib` components and dynamic code execution in `/repo/codenib/agent/tools/defaults.py`.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.
Files: codenib/cli.py, codenib/agent/route_context.py, codenib/eval/retrieval_eval.py and 3 more · reported by agent-audit-kit
9 YARA_code_execution_generic
Files: /repo/scripts/guardian/deepswe/harness/agent.py, /repo/codenib/compiler/snapshot_store.py, /repo/codenib/eval/benchmarks/swebench_policy_cases.py · reported by cisco-skill-scanner
6 AAK-TASKS-003
Files: scripts/swebench_graph_index.py, scripts/guardian/deepswe/harness/agent.py, codenib/sandbox/types.py and 3 more · reported by agent-audit-kit
4 COMMAND_INJECTION_EVAL
Files: /repo/codenib/index/rerank/cross_encoder.py, /repo/codenib/serving/server/hf_engine.py, /repo/codenib/serving/server/real_model.py and 1 more · reported by cisco-skill-scanner
3 FILE_MAGIC_MISMATCH
Files: /repo/core/CMakeLists.txt, /repo/codenib/model/prompts/agentless_stage2.txt · reported by cisco-skill-scanner
2 AAK-METIS-SCORING-SINK-001
Files: codenib/index/embedding/vector_store.py, codenib/eval/benchmarks/policy_benchmark.py · reported by agent-audit-kit
2 GLOB_HIDDEN_FILE_TARGETING
Files: /repo/codenib/graph/incremental/patcher_cpp.py · reported by cisco-skill-scanner
2 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/.claude/design/agent-runtime.md, /repo/scripts/embeddings/EMBEDDING_PROMPTS.md · reported by nerlo-install-instruction
1 AAK-ANTHROPIC-SDK-001
Files: scripts/smoke_release_services.py · reported by agent-audit-kit
1 AAK-HEALTHCARE-AI-004
Files: codenib/agent/skills/trace/skill.md · reported by agent-audit-kit
1 AAK-LEGAL-002
Files: web/package.json · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 HIDDEN_DATA_FILE
Files: /repo/.pre-commit-config.yaml · reported by cisco-skill-scanner
1 hooks-no-pretooluse
Files: settings.json · reported by agentshield
1 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/setup-scip.sh · reported by nerlo-install-instruction
1 opt.nerlo-rules.nerlo-py-dynamic-exec
Files: /repo/codenib/agent/tools/defaults.py · reported by nerlo-behavioral
1 PATH_TRAVERSAL_OPEN
Files: /repo/scripts/build_commit_window.py · reported by cisco-skill-scanner
1 permissions-no-block
Files: settings.json · reported by agentshield
1 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/codenib/web/launcher.py · reported by cisco-skill-scanner