Loading the registry…
Navigation OS for AI agents: map-first genetic tags, foundation pillars, indexes, genes, Cursor rules (platform 0.4.15)
We found this by crawling public sources and nobody has attested to it. That is how most of the registry gets here, and it is not a mark against the artifact — it only means no authenticated act of publication is on record. An artifact can be the vendor's own and still appear here.
90 critical findings reported by cisco-skill-scanner, 45 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 -- @agentstack/genetic-ai-starter
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
0 findings · 0.5s
v2.0.11
571 findings · 22.5s
v0.3.74
21 findings · 4.9s
v0.1.0
11 findings · 5.5s
v0.1.0
6 findings · 5.5s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 1.9s
v0.71.0
No dependency manifest or lockfile was found in this artifact. What each scanner covers
0 findings · 0.3s
v2.3.8
No dependency manifest or lockfile was found in this artifact. What each scanner covers
0 findings · 0.1s
v0.71.0
No container image was published for this artifact. What each scanner covers
0 findings · 0.0s
vv1.6.0
No Go modules were found in this artifact. What each scanner covers
0 findings · 0.1s
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 21, 2026 | Flagged42 | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source ·n/a: not applicabletrivy ·n/a: not applicableosv-scanner ·n/a: not applicabletrivy_image ·n/a: not applicablegovulncheck ·n/a: not applicable | completed |
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 609 findings across every scanner that examined this package. 45 of 90 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.
102 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-SECRET-004, opt.nerlo-rules.nerlo-js-secret-to-network-egress, FILE_MAGIC_MISMATCH and 7 more · Files: fixtures/empty-node-project/examples/agentstack/02-8dna-crud/run.ts, fixtures/empty-node-project/examples/agentstack/05-economy/run.ts, fixtures/empty-node-project/examples/agentstack/08-capability-task/run.ts and 57 more · reported by agent-audit-kit, nerlo-behavioral, cisco-skill-scanner and 1 more
94 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_JS_CHILD_PROCESS, DATA_EXFIL_JS_FS_ACCESS · Files: /repo/benchmarks/tests/prepare-arm.test.mjs, /repo/tests/agentstack-app-install.test.mjs, /repo/tests/agentstack-consumer-flow.test.mjs and 37 more · reported by 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.
179 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/benchmarks/scripts/aggregate-results.mjs, /repo/benchmarks/scripts/analyze-results.mjs, /repo/benchmarks/scripts/assert-channel.mjs and 52 more · reported by cisco-skill-scanner
48 MANIFEST_MISSING_LICENSE
Files: /repo/payload/.cursor/skills/agentstack-mcp-discover/SKILL.md, /repo/payload/.cursor/skills/bootstrap-subsystem/SKILL.md, /repo/payload/.cursor/skills/gene-first-debug/SKILL.md and 45 more · reported by cisco-skill-scanner
45 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/benchmarks/scripts/analyze-results.mjs, /repo/benchmarks/scripts/prepare-all-arms.mjs, /repo/benchmarks/scripts/prepare-arm.mjs and 21 more · reported by cisco-skill-scanner
38 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/payload/SKILL.md, /repo/template-repo/SKILL.md and 35 more · reported by cisco-skill-scanner
23 DATA_EXFIL_JS_NETWORK
Files: /repo/benchmarks/fixture-shop-api/src/lib/httpClient.ts, /repo/extensions/agentstack/recipes/01-discover-capabilities/run.ts, /repo/extensions/agentstack/recipes/03-mcp-execute/run.ts and 3 more · reported by cisco-skill-scanner
19 LOW_ANALYZABILITY
Files: /repo/extensions/agentstack/recipes/01-discover-capabilities, /repo/extensions/agentstack/recipes/02-8dna-crud, /repo/extensions/agentstack/recipes/06-logic and 16 more · reported by cisco-skill-scanner
15 YARA_capability_inflation_generic
Files: /repo/payload/philosophy/genes/GENE_INDEX.md, /repo/payload/philosophy/genes/repo.community.starter_spirit.gen1.md, /repo/payload/philosophy/genes/SKILL.md · reported by cisco-skill-scanner
9 FILE_MAGIC_MISMATCH
Files: /repo/benchmarks/fixture-shop-api/src/server.ts, /repo/benchmarks/fixture-shop-api/src/tools/devServer.ts, /repo/payload/templates/gitignore.genetic-ai.header.txt · reported by cisco-skill-scanner
8 AAK-SECRET-004
Files: extensions/agentstack/recipes-python/02-8dna-crud.py, extensions/agentstack/recipes-python/00-bootstrap.py, extensions/agentstack/recipes/02-8dna-crud/run.ts and 5 more · reported by agent-audit-kit
6 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/extensions/agentstack/recipes-python/03-mcp-execute.py · reported by cisco-skill-scanner
5 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/extensions/agentstack/recipes/01-discover-capabilities/run.ts, /repo/extensions/agentstack/recipes/03-mcp-execute/run.ts, /repo/extensions/agentstack/recipes/06-logic/run.ts and 2 more · reported by nerlo-behavioral
4 HIDDEN_DATA_FILE
Files: /repo/payload/.cursorrules.fragment.md, /repo/payload/.genetic-ai/kit.manifest.stub.json · reported by cisco-skill-scanner
4 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/README.en.md, /repo/scripts/install-here.ps1, /repo/scripts/lib/install-errors.mjs · reported by nerlo-install-instruction
3 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/repo/ADOPTERS.md, /repo/extensions/agentstack/repo/extensions/agentstack/AI_INDEX.md, /repo/extensions/agentstack/recipes-python/repo/extensions/agentstack/recipes-python/README.md · reported by cisco-skill-scanner
2 AAK-LEGAL-002
Files: extensions/agentstack/recipes/package.json, benchmarks/fixture-shop-api/package.json · reported by agent-audit-kit
2 LAZY_LOAD_DEEP_NESTING
Files: /repo/SKILL.md, /repo/payload/philosophy/genes/SKILL.md · reported by cisco-skill-scanner
1 AAK-SUPPLY-004
Files: package.json · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/extensions/agentstack/recipes-python/03-mcp-execute.py · reported by nerlo-behavioral
Artifact allows shell execution and exposes credentials with network egress.
The artifact contains numerous instances of potential shell command execution, particularly in JavaScript files within `benchmarks/scripts`, `bin`, and `scripts` directories. It also exposes credentials in 8 locations and facilitates network egress with secrets in 6 instances. These capabilities warrant close attention due to the potential for system compromise and data exposure.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Showing 25 of 59; the rest are in the per-scanner reports above.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.