Loading the registry…
agentdex-cli uv workspace root — orchestrator + plugin + engine + bridges + observability + KAOS
Cursor Rules are .cursorrules / .cursor/rules files that steer Cursor's AI; scanned with the same pipeline.
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.
10 critical findings reported by agent-audit-kit, 2 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
Cursor Rules are .cursorrules / .cursor/rules files that steer Cursor's AI. Review the scanned source before copying them into your own project.
nerlo install -- agentdex-cli-workspace
4 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
Incomplete run
0 findings · 213.6s
v0.3.74
104 findings · 196.9s
v0.1.0
10 findings · 35.4s
v0.1.0
3 findings · 35.4s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.2s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.2s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 1.6s
No report in this scan: 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 22, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner ·!: incompleteagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-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 117 findings across every scanner that examined this package. 8 of 10 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.
23 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-SECRET-002, AAK-SECRET-001, AAK-STDIO-001 and 5 more · Files: packages/agentdex_cli/tests/test_openbox_cmd.py, packages/agentdex_cli/tests/test_run_cmd.py, packages/kaos/tests/test_mcp_v091.py and 13 more · reported by agent-audit-kit
10 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-AGENT-TRUST-002, AAK-GHA-IMMUTABLE-001 · Files: .github/workflows/pr-cascade-breaker-gate.yml, .github/workflows/ga-enroll-invariants.yml, .github/workflows/ga-arena-modes-invariants.yml and 5 more · reported by agent-audit-kit
7 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-MCP-001, AAK-MCP-NOAUTH-DEFAULT, opt.nerlo-rules.nerlo-install-pipe-to-shell and 3 more · Files: examples/agent-starter-kit/.mcp.json, examples/agent-starter-kit/arena_mcp_proxy.py, /repo/docs/runbooks/badge-admin.md and 1 more · reported by agent-audit-kit, nerlo-install-instruction
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.
24 AAK-SECRET-004
Files: scripts/review_comment_signoff_gate.py, scripts/llm_proxy_measure.py, packages/agentdex_observe/src/agentdex_observe/llm_pool.py and 15 more · reported by agent-audit-kit
8 AAK-METIS-SCORING-SINK-001
Files: vendor/aaop/skillzero/recipe/spin/fsdp_workers.py, vendor/aaop/skillzero/verl/workers/fsdp_workers.py, vendor/aaop/skillzero/agent_system/environments/env_package/alfworld/alfworld/agents/modules/memory.py and 3 more · reported by agent-audit-kit
8 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/.fleet-goal/evidence/first-window/candidates/pokeagent-llm/agent.py, /repo/packages/agentdex_arena/src/agentdex_arena/gateway.py, /repo/packages/agentdex_cli/src/agentdex_cli/arena_ui.py and 5 more · reported by nerlo-behavioral
3 AAK-HEALTHCARE-AI-004
Files: blog/why-bene.md, sweeps/adx-cli-fleet-kanban.json, packages/kaos/README.md · reported by agent-audit-kit
3 AAK-MCP-ATTEST-001
Files: .factory/mcp.json · reported by agent-audit-kit
3 AAK-OAUTH-007
Files: packages/kaos/kaos/ccr/tools.py, packages/agentdex_arena/src/agentdex_arena/device_flow.py, .fleet-goal/evidence/M1/research/brief-weco.json · reported by agent-audit-kit
3 AAK-TASKS-003
Files: packages/adx_ladders/src/adx_ladders/adapters/tb2_harbor.py, packages/agentdex_engine/src/agentdex_engine/cards/task_card.py, packages/agentdex_engine/src/agentdex_engine/modules/tasks/models.py · reported by agent-audit-kit
2 AAK-LEGAL-002
Files: packages/adx_showdown/package.json, tools/ga_spa/package.json · reported by agent-audit-kit
2 AAK-OAUTH-005
Files: sweeps/adx-cli-fleet-kanban.json, packages/agentdex_arena/src/agentdex_arena/gateway.py · reported by agent-audit-kit
2 opt.nerlo-rules.nerlo-py-dynamic-exec
Files: /repo/packages/kaos/kaos/ccr/tools.py, /repo/packages/kaos/kaos/isolation.py · reported by nerlo-behavioral
1 AAK-HEALTHCARE-AI-005
Files: sweeps/adx-cli-fleet-kanban.json · reported by agent-audit-kit
1 AAK-IPI-WILD-CORPUS-001
Files: sweeps/adx-cli-fleet-kanban.json · reported by agent-audit-kit
1 AAK-MCP-001
Files: .factory/mcp.json · reported by agent-audit-kit
1 AAK-MCP-NOAUTH-DEFAULT
Files: packages/agentdex_arena/src/agentdex_arena/gateway.py · reported by agent-audit-kit
1 AAK-MCP-SDK-CVE-2026-52869-001
Files: uv.lock · reported by agent-audit-kit
1 AAK-MCP-TOOL-UNSAFE-EVAL-001
Files: vendor/aaop/a-evolve/agent_evolve/agents/arc/strands_agent.py · reported by agent-audit-kit
1 AAK-MCP-TOOLGATE-ASYMMETRY-001
Files: packages/kaos/kaos/mcp/server.py · reported by agent-audit-kit
1 AAK-OAUTH-001
Files: packages/kaos/kaos/ccr/tools.py · reported by agent-audit-kit
1 AAK-SKILL-UNTRUSTED-EXEC-PATH
Files: tools/agent_senses/fleet_kanban.py · reported by agent-audit-kit
1 AAK-SPLUNK-TOKLOG-001
Files: packages/agentdex_cli/src/agentdex_cli/cli.py · reported by agent-audit-kit
1 AAK-TASKS-001
Files: packages/agentdex_engine/src/agentdex_engine/modules/tasks/trivial.py · reported by agent-audit-kit
1 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/packages/kaos/README.md · reported by nerlo-install-instruction
1 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/.agents/skills/langfuse/SKILL.md · reported by nerlo-install-instruction
The model could have called any of these a false positive and did not.
6 AAK-METIS-SCORING-SINK-001
Files: vendor/aaop/skillzero/tests/e2e/arithmetic_sequence/rl/main_trainer.py, vendor/aaop/skillzero/examples/search/retriever/retrieval_server.py, vendor/aaop/skill1/tests/e2e/arithmetic_sequence/rl/main_trainer.py and 1 more · reported by agent-audit-kit
Critical risks from unsafe evaluation and control plane configuration
The artifact contains critical findings related to unsafe evaluation in `vendor/aaop/a-evolve/agent_evolve/agents/arc/strands_agent.py` and a critical control plane configuration issue in `.factory/mcp.json`. Multiple high-severity findings indicate potential credential access risks across various `agentdex` packages and `design` files. Other high-severity findings include an OAuth configuration in `packages/kaos/kaos/ccr/tools.py`, a Splunk token logging issue in `packages/agentdex_cli/src/agentdex_cli/cli.py`, and a task execution issue in `packages/agentdex_engine/src/agentdex_engine/modules/tasks/trivial.py`.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Showing 25 of 46; 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.