memorix · Nerlo

memorix

Name: memorix
Author: AVIDS2

Version: v1.3.0
By: AVIDS2
License: Apache-2.0
Last scan: Scanned Sep 11, 2026, 8:13 PM UTC

MCP Server

Scan Haltedcomposite

Local-first shared memory layer for AI coding agents across MCP clients, Git history, reasoning context, and project sessions.

Source:: github.com/AVIDS2/memorix
Version:: 1.3.0
License:: Apache-2.0
Author:: AVIDS2
Provenance:: Publisher-attested (provenance, not a security rating)
Registry namespace:: io.github.AVIDS2

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.

261 critical findings reported by cisco-skill-scanner, agent-audit-kit, 136 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/AVIDS2/memorix, 1149 findings

Install

Choose your runtime: the CLI writes the mcpServers config entry for that target.

nerlo install --target claude-code -- memorix

Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.

How scores work Full audit report

Per-scanner reports

7 scanners

Your view:

7 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.

Scanners that examined this package (7)

agentshield
v1.4.0
Clean100
- No findings
0 findings · 0.7s
cisco-skill-scanner
v2.0.11
Flagged0
- 227Crit
- 3High
- 46Med
- 26Low
- 617Info
919 findings · 56.2s

AI review of these findings

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.

Upheld as real: 536
Dismissed as false positives: 580
Not reviewed: 33

Out of 1,149 findings across every scanner that examined this package. 123 of 261 findings rated critical by their scanner were among the dismissals.

Not reviewed is not the same as clean. Those 33 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.

Why those were dismissed

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.

477 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, AAK-SECRET-002, SECRET_GOOGLE_API and 29 more · Files: /repo/tests/cli/agent-doctor.test.ts, /repo/tests/cli/codegraph-command.test.ts, /repo/tests/cli/context-command.test.ts and 138 more · reported by cisco-skill-scanner, agent-audit-kit
102 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: YARA_prompt_injection_generic, COMMAND_INJECTION_EVAL, COMMAND_INJECTION_JS_CHILD_PROCESS and 17 more · Files: /repo/packages/memcode/docs/sdk.md, /repo/packages/memcode/examples/sdk/03-custom-prompt.ts, /repo/packages/memcode/examples/sdk/README.md and 38 more · reported by cisco-skill-scanner, nerlo-behavioral, nerlo-install-instruction and 1 more
1 Placeholder value — The matched literal is a placeholder or example — the kind of value a scanner reads as a secret and a human reads as a blank to fill in.
Rules: YARA_credential_harvesting_generic · Files: /repo/tests/workspace/sanitizer.test.ts · reported by cisco-skill-scanner

In installed code — never dismissed

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.

117 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/packages/memcode/src/core/extensions/loader.ts, /repo/packages/memcode/src/modes/interactive/components/extension-editor.ts, /repo/packages/memcode/src/modes/interactive/interactive-mode.ts and 28 more · reported by cisco-skill-scanner
94 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/packages/memcode/src/core/footer-data-provider.ts, /repo/packages/memcode/src/core/resolve-config-value.ts, /repo/packages/memcode/src/modes/interactive/components/session-selector.ts and 22 more · reported by cisco-skill-scanner
68 DATA_EXFIL_JS_NETWORK
Files: /repo/packages/agent-core/src/proxy.ts, /repo/packages/ai/scripts/generate-image-models.ts, /repo/packages/ai/scripts/generate-models.ts and 23 more · reported by cisco-skill-scanner
55 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/codex/memorix/skills/memorix-sessions/SKILL.md, /repo/plugins/codex/memorix/skills/memorix-reasoning/SKILL.md, /repo/plugins/codex/memorix/skills/memorix-git-memory/SKILL.md and 52 more · reported by cisco-skill-scanner
19 COMMAND_INJECTION_EVAL

Not reviewed

31 The model did not answer for these findings.
Rules: AAK-TAINT-003 · Files: tests/integration/high-risk-fixes.test.ts, tests/integration/serve-http.test.ts, tests/integration/release-blockers.test.ts and 2 more · reported by agent-audit-kit
2 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: YARA_credential_harvesting_generic · Files: /repo/tests/media/audio-jobs.test.ts, /repo/tests/workspace/sanitizer.test.ts · reported by cisco-skill-scanner

What the review concluded

Critical command injection, server-side request forgery, and credential harvesting risks identified.

The artifact contains numerous critical command injection vulnerabilities, including via `eval` in `agent-core` and `memcode` packages, and through child processes in `memcode`. Server-side request forgery (SSRF) is present in `src/server.ts`, and DNS rebinding is identified in `src/cli/commands/serve-http.ts`. Additionally, the artifact exhibits credential harvesting capabilities and command injection via standard I/O in `src/cli/commands/serve.ts`.

Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.

What to look at

AAK-DNS-REBIND-001 · src/cli/commands/serve-http.ts · critical · reported by agent-audit-kit
AAK-MCP-STDIO-CMD-INJ-002 · src/cli/commands/serve.ts · critical · reported by agent-audit-kit
AAK-MCP-015 · src/dashboard/server.ts · critical · reported by agent-audit-kit
AAK-TAINT-001 · src/dashboard/server.ts · critical · reported by agent-audit-kit
AAK-SSRF-001 · src/server.ts · critical · reported by agent-audit-kit
AAK-TAINT-001 · src/server.ts · critical · reported by agent-audit-kit
AAK-TAINT-001 · src/server.ts · critical · reported by agent-audit-kit
AAK-TAINT-001 · src/server.ts · critical · reported by agent-audit-kit

Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.

Scan history

3 scans on record. Every scan's full results are retained immutably for 24 months.

Completed	Composite	Change	Scanners	Status
Sep 11, 2026	Scan Halted	—	agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·!: incompletenerlo-multi-source: complete	rejected
Aug 5, 2026	Pending scan	—	—	failed
Jul 31, 2026	Scan Halted	—	agentshield: completecisco-skill-scanner ·!: timeoutagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete	rejected

Per-scanner history:

AI review of these findings

Upheld as real: 536
Dismissed as false positives: 580
Not reviewed: 33

Out of 1,149 findings across every scanner that examined this package. 123 of 261 findings rated critical by their scanner were among the dismissals.

Not reviewed is not the same as clean. Those 33 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.

Why those were dismissed

477 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, AAK-SECRET-002, SECRET_GOOGLE_API and 29 more · Files: /repo/tests/cli/agent-doctor.test.ts, /repo/tests/cli/codegraph-command.test.ts, /repo/tests/cli/context-command.test.ts and 138 more · reported by cisco-skill-scanner, agent-audit-kit
102 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: YARA_prompt_injection_generic, COMMAND_INJECTION_EVAL, COMMAND_INJECTION_JS_CHILD_PROCESS and 17 more · Files: /repo/packages/memcode/docs/sdk.md, /repo/packages/memcode/examples/sdk/03-custom-prompt.ts, /repo/packages/memcode/examples/sdk/README.md and 38 more · reported by cisco-skill-scanner, nerlo-behavioral, nerlo-install-instruction and 1 more
1 Placeholder value — The matched literal is a placeholder or example — the kind of value a scanner reads as a secret and a human reads as a blank to fill in.
Rules: YARA_credential_harvesting_generic · Files: /repo/tests/workspace/sanitizer.test.ts · reported by cisco-skill-scanner

In installed code — never dismissed

117 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/packages/memcode/src/core/extensions/loader.ts, /repo/packages/memcode/src/modes/interactive/components/extension-editor.ts, /repo/packages/memcode/src/modes/interactive/interactive-mode.ts and 28 more · reported by cisco-skill-scanner
94 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/packages/memcode/src/core/footer-data-provider.ts, /repo/packages/memcode/src/core/resolve-config-value.ts, /repo/packages/memcode/src/modes/interactive/components/session-selector.ts and 22 more · reported by cisco-skill-scanner
68 DATA_EXFIL_JS_NETWORK
Files: /repo/packages/agent-core/src/proxy.ts, /repo/packages/ai/scripts/generate-image-models.ts, /repo/packages/ai/scripts/generate-models.ts and 23 more · reported by cisco-skill-scanner
55 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/codex/memorix/skills/memorix-sessions/SKILL.md, /repo/plugins/codex/memorix/skills/memorix-reasoning/SKILL.md, /repo/plugins/codex/memorix/skills/memorix-git-memory/SKILL.md and 52 more · reported by cisco-skill-scanner
19 COMMAND_INJECTION_EVAL

Not reviewed

31 The model did not answer for these findings.
Rules: AAK-TAINT-003 · Files: tests/integration/high-risk-fixes.test.ts, tests/integration/serve-http.test.ts, tests/integration/release-blockers.test.ts and 2 more · reported by agent-audit-kit
2 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: YARA_credential_harvesting_generic · Files: /repo/tests/media/audio-jobs.test.ts, /repo/tests/workspace/sanitizer.test.ts · reported by cisco-skill-scanner

What the review concluded

Critical command injection, server-side request forgery, and credential harvesting risks identified.

Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.

What to look at

AAK-DNS-REBIND-001 · src/cli/commands/serve-http.ts · critical · reported by agent-audit-kit
AAK-MCP-STDIO-CMD-INJ-002 · src/cli/commands/serve.ts · critical · reported by agent-audit-kit
AAK-MCP-015 · src/dashboard/server.ts · critical · reported by agent-audit-kit
AAK-TAINT-001 · src/dashboard/server.ts · critical · reported by agent-audit-kit
AAK-SSRF-001 · src/server.ts · critical · reported by agent-audit-kit
AAK-TAINT-001 · src/server.ts · critical · reported by agent-audit-kit
AAK-TAINT-001 · src/server.ts · critical · reported by agent-audit-kit
AAK-TAINT-001 · src/server.ts · critical · reported by agent-audit-kit

Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.

memorix

Install

Per-scanner reports

Scanners that examined this package (7)

agentshield

cisco-skill-scanner

agent-audit-kit

nerlo-skill-scanner (behavioral)

nerlo-skill-scanner (install-doc)

capslock

nerlo-multi-source

Scanners that did not run on this package (4)

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Not reviewed

What the review concluded

What to look at

Scan history

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Not reviewed

What the review concluded

What to look at

Install

Per-scanner reports

Scanners that examined this package (7)

agentshield

cisco-skill-scanner

agent-audit-kit

nerlo-skill-scanner (behavioral)

nerlo-skill-scanner (install-doc)

capslock

nerlo-multi-source

Scanners that did not run on this package (4)

Composite scoreOne view among many — the per-scanner reports above are primaryScan Halted

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Not reviewed

What the review concluded

What to look at

Scan history

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Not reviewed

What the review concluded

What to look at