Skills/npm/lemma

lemma@1.51.1

CAUTION· install only

Publisher claims: "Local MCP server that gives coding agents a verifiable project memory, trims what enters their context, and masks secrets — with honest accounting of what it saves and costs." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher nxuss · publishing for 196 daysInstalls 12,025Last detonated 5 h ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 7 of 7 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
ANTHROPIC_API_KEYANTHROPIC_AUTH_TOKENAUTH_ALLOWED_ORIGINSAUTH_ENABLEDAUTH_REQUIRE_API_KEYDATABASE_URLOPENAI_API_KEYConfiguration, not credentials: ANTHROPIC_BASE_URL, CHROMA_COLLECTION, CHROMA_HOST, CHROMA_PORT, CHROMA_URL, CODEX_BASE_URL, DASHBOARD_API_PORT, ENABLE_CACHING, IDE_SYNC_ENABLED, IDE_SYNC_EXPORT_PATH, IDE_SYNC_MODE, LEMMA_BIND_HOST, LEMMA_BRAIN_DIR, LEMMA_BRAIN_ENCRYPT, LEMMA_CACHE_DIR, LEMMA_CLOUD_KEY, LEMMA_CLOUD_URL, LEMMA_LEDGER_READONLY, LEMMA_LOG_DISABLE_CONSOLE, LEMMA_LOG_FILE, LEMMA_LOG_FORMAT, LEMMA_LOG_LEVEL, LEMMA_MCP_NO_PROXY, LEMMA_PROXY_PORT, LEMMA_QUIET, LEMMA_STOP_NUDGE, LITELLM_PROXY_BASE_URL, LOG_FILE, LOG_FORMAT, MAX_CACHE_SIZE, OLLAMA_HOST, OLLAMA_MODEL, OLLAMA_URL
Where it talks to
nxus.studio (its own)Also nodejs.org, lemma.dev, apple.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names nodejs.org, lemma.dev, apple.com as well as its own vendor. The guard injects ANTHROPIC_API_KEY, ANTHROPIC_AUTH_TOKEN, AUTH_ALLOWED_ORIGINS, AUTH_ENABLED, AUTH_REQUIRE_API_KEY, DATABASE_URL, OPENAI_API_KEY only into requests to nxus.studio (and its subdomains) and refuses the rest.

$vet-skills run --secrets ANTHROPIC_API_KEY=nxus.studio,ANTHROPIC_AUTH_TOKEN=nxus.studio,AUTH_ALLOWED_ORIGINS=nxus.studio,AUTH_ENABLED=nxus.studio,AUTH_REQUIRE_API_KEY=nxus.studio,DATABASE_URL=nxus.studio,OPENAI_API_KEY=nxus.studio -- npx -y @nxuss/lemma

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 1.49.1

vet-skills diff lemma 1.49.1 1.51.1

This version reaches for something 1.49.1 did not: 1 new host (nodejs.org) · 1 new install script (node bin/postinstall.js || true). Compared from the two recorded runs, not from source.

New hosts
nodejs.org
New install scripts
node bin/postinstall.js || true
No longer contacted
opencode.ai

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-19 and scored it 71/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: References a credential file in the home directory; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 2 s · 3 scenarios
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessbundled script run in the sandbox with no arguments
0.3sprocessbundled script run in the sandbox with no arguments
1.3sprocessexited 1: (Use `node --trace-warnings ...` to show where the warning was created)
1.3sprocessbundled script run in the sandbox with no arguments
1.4sfilesystemwrote ~/.lemma-cache/lemma_brain.json · ~/.lemma-cache/env
1.4sprocessbundled script run in the sandbox with no arguments
1.5sprocessbundled script run in the sandbox with no arguments
1.6sprocess7 of 7 bundled scripts run with no arguments
1.6sprocessscript backend runs setup only
1.6sprocessscript backend runs setup only
1.7sprocesssecond launch, clock +45 days, CI unset

Static findings

MEDIUM
npx invocation of non-well-known packagebin/init.js:428 · npx invocation of non-well-known package — may execute untrusted code> is installed, tell the user to run \`npx @nxuss/lemma init\`.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
References a credential file in the home directorydist/cjs/mcp/utils.js:419 · References a credential file in the home directory* `head $HOME/.ssh/id_rsa` and a symlink pointing out of the tree all pass the command allowlistFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
npx invocation of non-well-known packagebin/lemma-call.js:122 · npx invocation of non-well-known package — may execute untrusted codenpx @nxuss/lemma call <tool> [json] (via lemma-proxy.cjs)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/lemma-call.js:40 · npx invocation of non-well-known package — may execute untrusted codeexecSync('npx tsc --project tsconfig.cjs.json --outDir ./dist/cjs 2>&1', { cwd: path.join(__dirname, '..'), stdio: 'ignore', timeout: 30000 });Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Instructs the agent to modify its persistent memory or instruction filesbin/init.js:754 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file// Add AGENTS.md instructions path if supportedFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsdist/cjs/mcp/utils.js:418 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files* Keeps read-style commands inside the workspace. `cat /etc/passwd`, `ls ~`, `grep -r x ../..`,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagebin/lemma-call.js:14 · npx invocation of non-well-known package — may execute untrusted code* npx @nxuss/lemma call search_memory '{"query":"hello"}'Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Instructs the agent to modify its persistent memory or instruction filesbin/init.js:306 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file// 1. Write CLAUDE.md in project rootFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsdist/esm/mcp/prompts.js:108 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif (entry.name.startsWith(".") && entry.name !== ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagedist/cjs/mcp/utils.js:561 · npx invocation of non-well-known package — may execute untrusted code// this validator exists for. Agents append it by habit (`npx vitest run 2>&1 | tail -80`), and theFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/init.js:667 · npx invocation of non-well-known package — may execute untrusted codenpm i -D @nxuss/lemma && npx lemma initFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/init.js:272 · npx invocation of non-well-known package — may execute untrusted code// which is more than a native Bash rule like `Bash(npx jest *)` would. To tighten it: setFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
References a credential file in the home directorydist/esm/mcp/utils.js:399 · References a credential file in the home directory* `head $HOME/.ssh/id_rsa` and a symlink pointing out of the tree all pass the command allowlistFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
npx invocation of non-well-known packagebin/postinstall.js:54 · npx invocation of non-well-known package — may execute untrusted code* Only a global install is the moment someone is setting Lemma up. `npx -y @nxuss/lemma mcp`Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/esm/mcp/utils.js:541 · npx invocation of non-well-known package — may execute untrusted code// this validator exists for. Agents append it by habit (`npx vitest run 2>&1 | tail -80`), and theFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/init.js:602 · npx invocation of non-well-known package — may execute untrusted code…scapes the arguments. It is available as \`lemma call\` (global npm install), \`npx @nxuss/lemma call\`, or, inside the lemma repo, \`node ./lemma-proxy.cjs call\` / \`node ./b…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsdist/cjs/mcp/prompts.js:116 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif (entry.name.startsWith(".") && entry.name !== ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionbin/brain-ingest.js:18 · File type combined with upload action — agent may exfiltrate local data files* lemma-brain-ingest --hook-failure < payload.json (PostToolUseFailure: a failing Bash run, handled like --hook-result)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiondist/esm/embed/index.js:866 · File type combined with upload action — agent may exfiltrate local data filesthis.log(`📦 Stored: "${input.slice(0, 50)}..."`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiondist/cjs/embed/index.js:905 · File type combined with upload action — agent may exfiltrate local data filesthis.log(`📦 Stored: "${input.slice(0, 50)}..."`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packagebin/init.js:665 · npx invocation of non-well-known package — may execute untrusted codenpx @nxuss/lemma init # writes .agents/skills/lemma/SKILL.md and AGENTS.md in that projectFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsdist/esm/mcp/utils.js:398 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files* Keeps read-style commands inside the workspace. `cat /etc/passwd`, `ls ~`, `grep -r x ../..`,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈78 tok
1 file · 81 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for @nxuss/lemma@1.51.1 as of 4 h ago. This is the package itself, not its dependencies.

What would make this Verified

9 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim nxuss: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
  3. References a credential file in the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  6. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim nxussPropose a patch to the maintainer