Loading the registry…
Minni (ᛗ): local-first, multi-agent memory daemon — recall is evidence, not instruction.
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.
32 critical findings reported by cisco-skill-scanner, agent-audit-kit, 13 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 2 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.
github: https://github.com/infektyd/minni, 492 findings
Claude Skills install to a single target, no runtime picker.
nerlo install -- minni
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- minni ~/.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.
v2.0.11
404 findings · 32.7s
v0.3.74
76 findings · 57.6s
v0.1.0
7 findings · 40.1s
v0.1.0
5 findings · 40.2s
v0.1.0
0 findings · 56.3s
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 · 0.1s
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 ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: complete | rejected |
| Aug 11, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-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 492 findings across every scanner that examined this package. 19 of 32 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.
232 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, YARA_credential_harvesting_generic, COMMAND_INJECTION_JS_CHILD_PROCESS and 19 more · Files: tests/test_policy_redaction_contract_237.py, bench/tests/test_scrub.py, /repo/plugins/minni/tests/slice-f-hardening.test.mjs and 36 more · reported by agent-audit-kit, cisco-skill-scanner
49 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: YARA_system_manipulation_generic, PIPELINE_TAINT_FLOW, PROMPT_INJECTION_IGNORE_INSTRUCTIONS and 6 more · Files: /repo/tests/test_policy_redaction_contract_237.py, /repo/docs/contracts/POLICY.md, /repo/docs/contracts/SKILL.md and 19 more · reported by cisco-skill-scanner, nerlo-install-instruction, agent-audit-kit
35 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: YARA_credential_harvesting_generic, AAK-AGENT-TRUST-002, PIPELINE_TAINT_FLOW and 7 more · Files: /repo/.github/workflows/grok.yml, .github/workflows/claude.yml, /repo/.github/workflows/grok-boundary-test.yml and 6 more · reported by cisco-skill-scanner, agent-audit-kit, nerlo-behavioral
4 Agent instruction file — The match is in a file that instructs an AI coding agent — a CLAUDE.md or similar. It is documentation of intent, and our own check confirmed it is not part of what gets installed.
Rules: AAK-AGENT-002, TOOL_ABUSE_UNDECLARED_NETWORK · Files: AGENTS.md, /repo/repo/AGENTS.md, /repo/.github/repo/.github/APPROVAL_POLICY.md · 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.
33 HIDDEN_DATA_FILE
Files: /repo/plugins/minni/.kilocode-plugin/commands/recall.md, /repo/plugins/minni/.gemini-plugin/skills/sovereign-memory/SKILL.md, /repo/plugins/minni/.kilocode-plugin/commands/audit.md and 17 more · reported by cisco-skill-scanner
32 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/minni/.kilocode-plugin/skills/sovereign-memory/SKILL.md, /repo/plugins/minni/skills/readme-audit/SKILL.md, /repo/plugins/minni/skills/minni-install/SKILL.md and 29 more · reported by cisco-skill-scanner
22 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/.grok/SKILL.md, /repo/bench/SKILL.md and 19 more · reported by cisco-skill-scanner
11 AAK-SECRET-004
Files: plugins/minni/frontend/app.js, plugins/minni/src/task.ts, plugins/minni/src/vault.ts and 2 more · reported by agent-audit-kit
10 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/plugins/minni/src/team-vault-bootstrap.ts · reported by cisco-skill-scanner
The model could have called any of these a false positive and did not.
4 SQL_INJECTION_STRING_FORMAT
Files: /repo/src/minni/afm_passes/vault_ingest.py, /repo/src/minni/wiki_indexer.py, /repo/src/minni/repair_dual_candidates.py and 1 more · reported by cisco-skill-scanner
Critical SQL injection and credential exposure risks identified.
The artifact contains multiple critical SQL injection vulnerabilities in Python files, which could allow unauthorized database manipulation. High-severity findings indicate potential credential exposure in JavaScript files and secrets being sent over the network, leading to network egress. Additionally, the artifact exhibits file system access capabilities and potential resource abuse through infinite loops.
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.
5 FILE_MAGIC_MISMATCH
Files: /repo/.cursor/approval-policies/ROUTING.md, /repo/plugins/minni/src/codex-hook.ts · reported by cisco-skill-scanner
4 DATA_EXFIL_JS_NETWORK
Files: /repo/plugins/minni/frontend-src/src/api.ts, /repo/scripts/afm-sovereign-scenarios.mjs, /repo/scripts/afm-swift-knowledge.mjs · reported by cisco-skill-scanner
4 MANIFEST_INVALID_NAME
Files: /repo/.cursor/SKILL.md, /repo/src/minni/afm_prompts/SKILL.md, /repo/.githooks/SKILL.md and 1 more · reported by cisco-skill-scanner
4 opt.nerlo-rules.nerlo-install-shell-inline-command
Files: /repo/plugins/minni/skills/minni-consolidation/SKILL.md, /repo/plugins/minni/skills/minni-health-check/SKILL.md, /repo/plugins/minni/skills/minni-install/scripts/propagate.py · reported by nerlo-install-instruction
4 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/plugins/minni/frontend-src/src/api.ts, /repo/plugins/minni/frontend/app.js, /repo/scripts/afm-sovereign-scenarios.mjs and 1 more · reported by nerlo-behavioral
4 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/src/minni/afm_writer.py, /repo/src/minni/minnid.py, /repo/src/minni/minnid_runtime/handoff.py and 1 more · reported by cisco-skill-scanner
4 SECRET_PASSWORD_VAR
Files: /repo/bench/membench/scrub.py · reported by cisco-skill-scanner
4 YARA_sql_injection_generic
Files: /repo/src/minni/afm_passes/consolidation.py, /repo/src/minni/afm_passes/unpark_privacy_backlog.py, /repo/src/minni/afm_review_markers.py · reported by cisco-skill-scanner
3 AAK-IPI-WILD-CORPUS-001
Files: plugins/minni/skills/minni-ingestion/SKILL.md, src/minni/migrations.py, bench/membench/adapters/llm_wiki.py · reported by agent-audit-kit
2 AAK-MCP-ATTEST-001
Files: plugins/minni/.mcp.json, plugins/minni/.kilocode-plugin/.mcp.json · reported by agent-audit-kit
2 AAK-SKILL-001
Files: plugins/minni/skills/minni-health-check/SKILL.md, plugins/minni/skills/minni-consolidation/SKILL.md · reported by agent-audit-kit
2 AAK-SPLUNK-TOKLOG-001
Files: plugins/minni/src/config.ts, plugins/minni/src/ui-server.ts · reported by agent-audit-kit
2 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/src/minni/afm_provider.py · reported by cisco-skill-scanner
2 EXCESSIVE_FILE_COUNT
Files: /repo/., /repo/plugins/minni/. · reported by cisco-skill-scanner
2 LOW_ANALYZABILITY
Files: /repo/plugins/minni, /repo · reported by cisco-skill-scanner
2 SQL_INJECTION_STRING_FORMAT
Files: /repo/src/minni/backfill.py · reported by cisco-skill-scanner
1 AAK-ANTHROPIC-SDK-001
Files: plugins/minni/src/server.ts · reported by agent-audit-kit
1 AAK-HEALTHCARE-AI-004
Files: plugins/minni/skills/minni-install/SKILL.md · reported by agent-audit-kit
1 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
1 AAK-MCP-014
Files: plugins/minni/src/ui-server.ts · reported by agent-audit-kit
1 AAK-MCP-018
Files: plugins/minni/src/server.ts · reported by agent-audit-kit
1 AAK-MCP-OPENCLAW-CVE-2026-62195-001
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-MCP-SSRF-001
Files: plugins/minni/frontend-src/src/api.ts · reported by agent-audit-kit
1 AAK-MCP-STDIO-LAUNCHER-INJECT-001
Files: plugins/minni/.kilocode-plugin/.mcp.json · reported by agent-audit-kit
1 AAK-TAINT-001
Files: plugins/minni/src/ui-server.ts · reported by agent-audit-kit
1 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/bench/repo/bench/README.md · reported by cisco-skill-scanner
Showing 25 of 53; the rest are in the per-scanner reports above.