Loading the registry…
Cross-platform decision evidence and reconstruction for regulated AI 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.
4 critical findings reported by cisco-skill-scanner, agent-audit-kit, 2 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 3 sources and their verdicts differ. The worst is github (Flagged). Installing from a cleaner source does not mean the others are safe — check the source you actually install from. Some sources have no verdict at all; that is not a pass.
github: https://github.com/Lians-ai/Lians, 156 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- lians
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
5 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.
v2.0.11
77 findings · 20.2s
v0.3.26
34 findings · 16.5s
v0.1.0
2 findings · 33.0s
v0.1.0
0 findings · 33.0s
v0.1.0
0 findings · 22.9s
v1.4.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 0.2s
No report in this scan: capslock, govulncheck, osv-scanner, trivy, trivy_image.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 3, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | 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 113 findings across every scanner that examined this package. 2 of 4 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.
25 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-HEALTHCARE-AI-005, AAK-HEALTHCARE-AI-004, SOCIAL_ENG_VAGUE_DESCRIPTION and 1 more · Files: docs/hipaa.md, docs/institutional-proof-kit.md, docs/verticals.md and 15 more · reported by agent-audit-kit, cisco-skill-scanner
16 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: AAK-INDIA-PII-001, AAK-IPI-WILD-CORPUS-001, AAK-SECRET-004 and 2 more · Files: agentmem/tests/test_audit_chain.py, agentmem/tests/test_admission.py, agentmem/tests/test_memory_feedback.py and 9 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.
18 MANIFEST_MISSING_LICENSE
Files: /repo/skills/lians/SKILL.md, /repo/skills/lians-integrate/SKILL.md, /repo/integrations/lians-plugin/skills/lians-memory/SKILL.md and 15 more · reported by cisco-skill-scanner
13 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/skills/SKILL.md, /repo/packages/agentmem-backtest-check/SKILL.md and 10 more · reported by cisco-skill-scanner
4 AAK-HEALTHCARE-AI-004
Files: README.md, integrations/codex/README.md, integrations/lians-plugin/commands/lians-remember.md and 1 more · reported by agent-audit-kit
4 AAK-SECRET-004
Files: agentmem/benchmarks/tenant_isolation_eval.py, agentmem/benchmarks/http_load_eval.py, agentmem/src/lians/adapters/finance/__init__.py · reported by agent-audit-kit
4 HIDDEN_DATA_FILE
Files: /repo/integrations/mcpb/.mcpbignore, /repo/.artifacts/mcp-smoke.db, /repo/agentmem/.env.demo · reported by cisco-skill-scanner
Critical SQL injection and high-risk credential exposure detected.
The artifact contains critical SQL injection vulnerabilities in `/repo/agentmem/scripts/verify_pgvector.py`, which could allow unauthorized database manipulation. Multiple high-severity findings indicate potential credential exposure in `agentmem/benchmarks/` and `agentmem/src/lians/adapters/finance/__init__.py`. Additionally, the artifact exhibits high-risk behaviors such as potential infinite loops in `lians/client.py`, `lians/durable_jobs.py`, and `lians/scheduler.py`, and secret-to-network egress in `sdk/typescript/src/client.ts` and `sdk/python/src/lians/client.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.
4 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/agentmem/sdk/python/lians/client.py, /repo/agentmem/src/lians/durable_jobs.py, /repo/agentmem/src/lians/scheduler.py · reported by cisco-skill-scanner
2 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/integrations/grafana-lians-app/scripts/build-and-inspect.cjs · reported by cisco-skill-scanner
2 DATA_EXFIL_JS_NETWORK
Files: /repo/agentmem/sdk/typescript/src/client.ts · reported by cisco-skill-scanner
2 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/scripts/check_published_artifacts.py · reported by cisco-skill-scanner
2 FILE_MAGIC_MISMATCH
Files: /repo/agentmem/sdk/c/CMakeLists.txt · reported by cisco-skill-scanner
2 LOW_ANALYZABILITY
Files: /repo/integrations/grafana-lians-app, /repo/agentmem/sdk/typescript · reported by cisco-skill-scanner
2 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/repo/CHANGELOG.md, /repo/agentmem/sdk/python/repo/agentmem/sdk/python/README.md · reported by cisco-skill-scanner
2 YARA_sql_injection_generic
Files: /repo/agentmem/scripts/verify_pgvector.py · reported by cisco-skill-scanner
1 AAK-DNS-REBIND-002
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-LEGAL-002
Files: integrations/grafana-lians-app/package.json · reported by agent-audit-kit
1 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
1 AAK-SUPPLY-004
Files: pyproject.toml · reported by agent-audit-kit
1 ARCHIVE_FILE_DETECTED
Files: /repo/output/pdf/arxiv-regulated-memory-eval-source.zip · reported by cisco-skill-scanner
1 ASSET_PROMPT_INJECTION
Files: /repo/agentmem/benchmarks/data/locomo10.json · reported by cisco-skill-scanner
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/agentmem/sdk/typescript/src/client.ts · reported by nerlo-behavioral
1 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/sdk/python/src/lians/client.py · reported by nerlo-behavioral
1 UNANALYZABLE_BINARY
Files: /repo/output/pdf/arxiv-regulated-memory-eval-source.zip · reported by cisco-skill-scanner
1 YARA_prompt_injection_unicode_steganography
Files: /repo/tmp/pdfs/regulated-memory-eval/page-3.png · reported by cisco-skill-scanner