Loading the registry…
**Persistent, consensus-validated memory infrastructure for 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.
21 critical findings reported by cisco-skill-scanner, agent-audit-kit, 10 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- sage
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.
v1.4.0
4 findings · 1.4s
v2.0.11
251 findings · 32.3s
v0.3.26
36 findings · 36.9s
v0.1.0
25 findings · 100.3s
v0.1.0
5 findings · 100.3s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 17.8s
No report in this scan: capslock, govulncheck, osv-scanner, trivy, trivy_image.
3 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 3, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source ·n/a: not applicable | rejected |
| Jul 30, 2026 | Scan Halted | — | cisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source ·n/a: not applicable | rejected |
| Jul 30, 2026 | Scan Halted | — | cisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source ·n/a: not applicable | 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 321 findings across every scanner that examined this package. 11 of 21 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.
30 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: YARA_sql_injection_generic, SECRET_CONNECTION_STRING, PIPELINE_TAINT_FLOW and 7 more · Files: /repo/sdk/python/examples/complete_walkthrough.py, /repo/docs/ARCHITECTURE.md, /repo/docs/SKILL.md and 10 more · reported by cisco-skill-scanner, nerlo-behavioral, nerlo-install-instruction and 1 more
22 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, YARA_credential_harvesting_generic, COMMAND_INJECTION_JS_FUNCTION_CONSTRUCTOR and 7 more · Files: web/wizard_chatgpt_test.go, /repo/cmd/sage-gui/quorum_test.go, /repo/scripts/cerebrum-shell.test.mjs and 7 more · reported by agent-audit-kit, cisco-skill-scanner, nerlo-behavioral
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.
124 DATA_EXFIL_JS_NETWORK
Files: /repo/extension/chrome/background.js, /repo/web/static/js/api.js, /repo/web/static/js/app.js and 1 more · reported by cisco-skill-scanner
19 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/natter/SKILL.md, /repo/papers/SKILL.md and 16 more · reported by cisco-skill-scanner
19 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/natter/SKILL.md, /repo/papers/SKILL.md and 16 more · reported by cisco-skill-scanner
18 AAK-MCP-OPENAPI-LAZY-DESCRIPTION-001
Files: api/openapi.yaml · reported by agent-audit-kit
13 opt.nerlo-rules.nerlo-go-secret-to-network-egress
Files: /repo/api/rest/oauth_handlers.go, /repo/api/rest/server.go, /repo/cmd/sage-gui/node.go and 5 more · reported by nerlo-behavioral
9
The model could have called any of these a false positive and did not.
3 OBFUSCATION_XOR_ENCODING
Files: /repo/extension/chrome/icons/generate-icons.js · reported by cisco-skill-scanner
Artifact contains critical command injection and secret egress risks.
The artifact exhibits critical command injection vulnerabilities in JavaScript files like `sage-graph.bundle.js` and `check-static-js.mjs`, and shell execution patterns in `run-v11.9-state-sync.sh`. It also includes high-severity findings for potential secret exposure in files such as `deploy/init-testnet.sh` and `internal/store/badger.go`. Furthermore, the artifact demonstrates secret-to-network egress capabilities in Go code, specifically within `api/rest/oauth_handlers.go`, and other JavaScript and Python components.
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: /repo/papers/Paper2 - Consensus-Validated Memory Improves Agent Performance on Complex Tasks.pdf, /repo/papers/Paper4 - Longitudinal Learning in Governed Multi-Agent Systems - How Institutional Memory Improves Agent Performance Over Time.pdf, /repo/papers/Paper1 - Agent Memory Infrastructure - Byzantine-Resilient Institutional Memory for Multi-Agent Systems.pdf and 2 more · reported by cisco-skill-scanner
7 COMMAND_INJECTION_JS_FUNCTION_CONSTRUCTOR
Files: /repo/web/static/js/vendor/sage-graph.bundle.js · reported by cisco-skill-scanner
7 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/bench/locomo/run.py, /repo/bench/longmemeval/run.py, /repo/integrations/levelup/sage_bridge.py · reported by cisco-skill-scanner
7 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/extension/chrome/background.js, /repo/web/static/js/api.js, /repo/web/static/js/mri-brain.js · reported by nerlo-behavioral
4 AAK-SECRET-004
Files: deploy/init-testnet.sh, scripts/setup_studio_org.py, third_party/cometbft/light/store/db/db.go and 1 more · reported by agent-audit-kit
4 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/repo/CONTRIBUTING.md, /repo/bench/locomo/repo/bench/locomo/README.md, /repo/bench/longmemeval/repo/bench/longmemeval/README.md and 1 more · reported by cisco-skill-scanner
4 YARA_prompt_injection_unicode_steganography
Files: /repo/papers/Paper3 - Institutional Memory as Organizational Knowledge - AI Agents That Learn Their Jobs from Experience Not Instructions.pdf · reported by cisco-skill-scanner
3 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/extension/chrome/icons/generate-icons.js · reported by cisco-skill-scanner
3 LOW_ANALYZABILITY
Files: /repo/papers, /repo/extension, /repo/extension/chrome · reported by cisco-skill-scanner
2 EXCESSIVE_FILE_COUNT
Files: /repo/third_party/cometbft/., /repo/. · reported by cisco-skill-scanner
2 FIND_EXEC_PATTERN
Files: /repo/deploy/scripts/run-v11.9-state-sync.sh · reported by cisco-skill-scanner
2 hooks-no-pretooluse
Files: settings.json, .claude/settings.json · reported by agentshield
2 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/integrations/levelup/sage_bridge.py · reported by nerlo-behavioral
2 PDF_STRUCTURAL_THREAT
Files: /repo/papers/Paper3 - Institutional Memory as Organizational Knowledge - AI Agents That Learn Their Jobs from Experience Not Instructions.pdf · reported by cisco-skill-scanner
2 permissions-no-deny-list
Files: settings.json, .claude/settings.json · reported by agentshield
1 AAK-HEALTHCARE-AI-004
Files: README.md · reported by agent-audit-kit
1 AAK-HEALTHCARE-AI-005
Files: README.md · reported by agent-audit-kit
1 AAK-OAUTH-005
Files: api/openapi.yaml · reported by agent-audit-kit
1 AAK-SUPPLY-004
Files: package.json · reported by agent-audit-kit
1 AAK-TASKS-003
Files: web/static/js/api.js · reported by agent-audit-kit
1 AAK-TRUST-004
Files: .claude/settings.json · reported by agent-audit-kit
1 AAK-TRUST-006
Files: .claude/settings.json · reported by agent-audit-kit
1 BINARY_FILE_DETECTED
Files: /repo/installer/macos/AppIcon.icns · reported by cisco-skill-scanner
1 COMMAND_INJECTION_EVAL
Files: /repo/web/static/js/vendor/sage-graph.bundle.js · reported by cisco-skill-scanner
1 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/scripts/check-static-js.mjs · reported by cisco-skill-scanner
1 COMPOUND_FIND_EXEC
Files: /repo/deploy/scripts/run-v11.9-state-sync.sh · reported by cisco-skill-scanner
1 FILE_MAGIC_MISMATCH
Files: /repo/playwright.config.js · reported by cisco-skill-scanner
1 HIDDEN_DATA_FILE
Files: /repo/.golangci.yml · reported by cisco-skill-scanner
Showing 25 of 44; the rest are in the per-scanner reports above.