Loading the registry…
A lightweight, local-first, always-on personal AI agent built with TypeScript and the OpenAI Agents SDK.
Claude Skills are markdown + scripts loaded into Claude Code; 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.
16 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.
Claude Skills install to a single target, no runtime picker.
nerlo install -- mimi-agent
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- mimi-agent ~/.claude/skills/
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
124 findings · 18.6s
v0.3.74
119 findings · 20.8s
v0.1.0
22 findings · 11.2s
v0.1.0
17 findings · 11.2s
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
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image.
2 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Sep 3, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source ·n/a: not applicable | rejected |
| Aug 8, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·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 282 findings across every scanner that examined this package. 11 of 16 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.
98 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_FUNCTION_CONSTRUCTOR, AAK-TAINT-001, COMMAND_INJECTION_JS_CHILD_PROCESS and 6 more · Files: /repo/tests/macos-contacts-connector.test.ts, /repo/tests/macos-desktop-connector.test.ts, /repo/tests/macos-life-connector.test.ts and 17 more · reported by cisco-skill-scanner, agent-audit-kit
24 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-MARKETPLACE-001, opt.nerlo-rules.nerlo-install-fetch-raw-then-run, opt.nerlo-rules.nerlo-install-pipe-to-shell and 3 more · Files: skills/agent-skill-creator/references/examples/stock-analyzer/.claude-plugin/marketplace.json, skills/agent-skill-creator/.github/plugin/marketplace.json, /repo/skills/agent-skill-creator/docs/index.html and 10 more · reported by agent-audit-kit, nerlo-install-instruction, cisco-skill-scanner
2 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: MANIFEST_INVALID_NAME · Files: /repo/skills/agent-skill-creator/.github/ISSUE_TEMPLATE/SKILL.md, /repo/skills/agent-skill-creator/.github/SKILL.md · 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.
13 MANIFEST_MISSING_LICENSE
Files: /repo/skills/code-review/SKILL.md, /repo/skills/research/SKILL.md, /repo/skills/pdf/SKILL.md and 10 more · reported by cisco-skill-scanner
11 DATA_EXFIL_JS_NETWORK
Files: /repo/src/runtime/providers/anthropic.ts, /repo/src/runtime/providers/google.ts, /repo/src/runtime/providers/native-model.ts and 3 more · reported by cisco-skill-scanner
9 AAK-SECRET-004
Files: src/core/data-sanitizer.ts, src/daemon/memory-observation-store.ts, src/daemon/worker-protocol.ts and 4 more · reported by agent-audit-kit
9 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/src/runtime/providers/anthropic.ts, /repo/src/runtime/providers/google.ts, /repo/src/runtime/providers/native-model.ts and 3 more · reported by nerlo-behavioral
8 AAK-TASKS-003
Files: src/core/team.ts, src/daemon/store.ts, src/daemon/memory-observation-store.ts and 5 more · reported by agent-audit-kit
The model could have called any of these a false positive and did not.
12 COMMAND_INJECTION_SHELL_TRUE
Files: /repo/skills/agent-skill-creator/references/examples/pr-blocker-summarizer/scripts/run_evals.py, /repo/skills/agent-skill-creator/references/examples/stock-analyzer/scripts/run_evals.py, /repo/skills/agent-skill-creator/references/examples/weekly-crm-report/scripts/run_evals.py · reported by cisco-skill-scanner
6 opt.nerlo-rules.nerlo-py-dynamic-exec
Files: /repo/skills/agent-skill-creator/references/examples/pr-blocker-summarizer/scripts/run_evals.py, /repo/skills/agent-skill-creator/references/examples/stock-analyzer/scripts/run_evals.py, /repo/skills/agent-skill-creator/references/examples/weekly-crm-report/scripts/run_evals.py · reported by nerlo-behavioral
5 AAK-SECRET-004
Files: tests/connector-worker-rpc-boundary.test.ts, skills/agent-skill-creator/references/examples/weekly-crm-report/scripts/run_evals.py, skills/agent-skill-creator/references/examples/stock-analyzer/scripts/run_evals.py and 1 more · reported by agent-audit-kit
4 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/skills/agent-skill-creator/references/examples/weekly-crm-report/repo/skills/agent-skill-creator/references/examples/weekly-crm-report/SKILL.md, /repo/skills/agent-skill-creator/references/examples/stock-analyzer/repo/skills/agent-skill-creator/references/examples/stock-analyzer/SKILL.md, /repo/skills/agent-skill-creator/references/examples/pr-blocker-summarizer/repo/skills/agent-skill-creator/references/examples/pr-blocker-summarizer/SKILL.md and 1 more
Critical risks from command injection and sensitive data handling
The artifact contains critical command injection vulnerabilities in `src/tools.ts` and `src/daemon/ipc.ts`, allowing arbitrary shell execution. It also handles sensitive data flows in `scripts/run-browser-e2e.ts` and `scripts/run-mimi-browser-e2e.ts`. High severity findings indicate potential credential access in multiple `src/daemon` files and network egress of secrets from Python and JavaScript components. Additionally, the artifact performs dynamic code execution in Python and has numerous instances of shell command injection.
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.
8 HIDDEN_DATA_FILE
Files: /repo/skills/agent-skill-creator/.cursor-plugin/plugin.json, /repo/skills/agent-skill-creator/.agents/plugins/marketplace.json, /repo/skills/agent-skill-creator/.cursor-plugin/marketplace.json and 1 more · reported by cisco-skill-scanner
7 opt.nerlo-rules.nerlo-install-fetch-raw-then-run
Files: /repo/skills/agent-skill-creator/README.md, /repo/skills/agent-skill-creator/scripts/bootstrap.bat, /repo/skills/agent-skill-creator/scripts/bootstrap.ps1 and 1 more · reported by nerlo-install-instruction
6 COMMAND_INJECTION_SHELL_TRUE
Files: /repo/skills/agent-skill-creator/scripts/security_scan.py, /repo/skills/agent-skill-creator/scripts/run_evals_template.py · reported by cisco-skill-scanner
6 PIPELINE_TAINT_FLOW
Files: /repo/skills/agent-skill-creator/CHANGELOG.md, /repo/skills/agent-skill-creator/scripts/bootstrap.sh, /repo/skills/agent-skill-creator/README.md · reported by cisco-skill-scanner
5 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/knowledge/SKILL.md, /repo/skills/agent-skill-creator/references/SKILL.md and 2 more · reported by cisco-skill-scanner
4 AAK-MARKETPLACE-001
Files: skills/agent-skill-creator/.cursor-plugin/marketplace.json, skills/agent-skill-creator/.claude-plugin/marketplace.json, skills/agent-skill-creator/scripts/claude-plugin-template/marketplace.json and 1 more · reported by agent-audit-kit
3 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/skills/agent-skill-creator/CHANGELOG.md, /repo/skills/agent-skill-creator/README.md, /repo/skills/agent-skill-creator/scripts/bootstrap.sh · reported by nerlo-install-instruction
3 opt.nerlo-rules.nerlo-install-shell-inline-command
Files: /repo/skills/agent-skill-creator/README.md, /repo/skills/agent-skill-creator/scripts/bootstrap.bat, /repo/skills/agent-skill-creator/scripts/bootstrap.ps1 · reported by nerlo-install-instruction
2 AAK-HEALTHCARE-AI-004
Files: skills/computer-use/SKILL.md, skills/agent-skill-creator/CHANGELOG.md · reported by agent-audit-kit
2 AAK-MCP-007
Files: mcp.example.json · reported by agent-audit-kit
2 AAK-MCP-ATTEST-001
Files: mcp.example.json · reported by agent-audit-kit
2 AAK-OAUTH-007
Files: src/extensions/computer/manager.ts, skills/agent-skill-creator/scripts/security_scan.py · reported by agent-audit-kit
2 AAK-TAINT-001
Files: scripts/run-browser-e2e.ts, scripts/run-mimi-browser-e2e.ts · reported by agent-audit-kit
2 AAK-TAINT-003
Files: src/daemon/ipc.ts · reported by agent-audit-kit
2 AAK-TASKS-004
Files: src/daemon/store.ts, src/daemon/memory-observation-store.ts · reported by agent-audit-kit
2 EXCESSIVE_FILE_COUNT
Files: /repo/., /repo/skills/agent-skill-creator/. · reported by cisco-skill-scanner
2 FILE_MAGIC_MISMATCH
Files: /repo/skills/agent-skill-creator/scripts/claude-plugin-template/plugin.json · reported by cisco-skill-scanner
2 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/skills/agent-skill-creator/SKILL.md, /repo/skills/agent-skill-creator/references/interactive-mode.md · reported by nerlo-install-instruction
2 opt.nerlo-rules.nerlo-py-dynamic-exec
Files: /repo/skills/agent-skill-creator/scripts/run_evals_template.py · reported by nerlo-behavioral
2 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/skills/agent-skill-creator/repo/skills/agent-skill-creator/SKILL.md, /repo/skills/agent-skill-creator/references/repo/skills/agent-skill-creator/references/agentdb-integration.md · reported by cisco-skill-scanner
1 AAK-MARKETPLACE-004
Files: skills/agent-skill-creator/.agents/plugins/marketplace.json · reported by agent-audit-kit
1 AAK-MCP-005
Files: mcp.example.json · reported by agent-audit-kit
1 AAK-MCP-015
Files: src/daemon/ipc.ts · reported by agent-audit-kit
1 AAK-OAUTH-001
Files: src/extensions/computer/manager.ts · reported by agent-audit-kit
1 AAK-OAUTH-008
Files: mcp.example.json · reported by agent-audit-kit
1 COMMAND_INJECTION_EVAL
Files: /repo/src/tools.ts · reported by cisco-skill-scanner
1 FIND_EXEC_PATTERN
Files: /repo/skills/agent-skill-creator/references/SKILL.md · reported by cisco-skill-scanner
1 LOW_ANALYZABILITY
Files: /repo · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/skills/agent-skill-creator/scripts/run_evals_template.py · reported by nerlo-behavioral
1 SOCIAL_ENG_MISLEADING_DESC
Files: /repo/skills/agent-skill-creator/SKILL.md · reported by cisco-skill-scanner
1 YARA_prompt_injection_generic
Files: /repo/evals/security-policy-cases.json · reported by cisco-skill-scanner
3 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/skills/agent-skill-creator/references/examples/pr-blocker-summarizer/scripts/run_evals.py, /repo/skills/agent-skill-creator/references/examples/stock-analyzer/scripts/run_evals.py, /repo/skills/agent-skill-creator/references/examples/weekly-crm-report/scripts/run_evals.py · reported by nerlo-behavioral
1 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/examples/connectors/radar-connector.mjs · reported by nerlo-behavioral
Showing 25 of 82; the rest are in the per-scanner reports above.