Skills/ClawHub/local-self-healing-machine-learning

local-self-healing-machine-learning@2.0.1

CAUTION· static only

Publisher claims: "A fully local machine learning engine that makes your OpenClaw agent smart over time — without ever calling home, revealing your machine ID, or exposing any..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher josephtandle · publishing for 251 daysInstalls 1,413Last detonated 1 h ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-17 and scored it 45/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Pipe-to-shell pattern; Access to sensitive file paths; Access to sensitive file paths. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

HIGH
Pipe-to-shell patternSKILL.md:43 · Pipe-to-shell pattern — downloads and immediately executes remote codecurl -fsSL https://ollama.com/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Access to sensitive file pathsindex.js:5 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filestry { require('dotenv').config({ path: path.resolve(__dirname, './.env') }); } catch (e) { console.warn('[LSHML] Warning: dotenv not found or failed to load .env'); }Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsindex.js:4 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files// Hardened Env Loading: Ensure .env is loaded before anything elseFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
GitHub token pattern detectedtest/sanitize.test.js:19 · GitHub token pattern detected — possible hardcoded or harvested tokenassert.ok(redactString('ghp_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx1234').includes(REDACTED),Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
AWS access key pattern detectedtest/sanitize.test.js:29 · AWS access key pattern detected — possible hardcoded or harvested keyassert.ok(redactString('AKIAIOSFODNN7EXAMPLE').includes(REDACTED),Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
HIGH
Access to sensitive file pathssrc/gep/solidify.js:524 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files'.env',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/gep/sanitize.js:37 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files// .env file referencesFix: 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 actionsrc/gep/solidify.js:117 · File type combined with upload action — agent may exfiltrate local data filesexcludeExact: ['event.json', 'temp_gep_output.json', 'temp_evolution_output.json', 'evolution_error.log'],Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathssrc/gep/prompt.js:455 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesUse process.env or .env references. Hardcoded App ID, App Secret, Bearer tokens = FAILED.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/evolve.js:48 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files// dotenv might not be installed or .env missing, proceed gracefullyFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Remote installer piped to shellSKILL.md:43 · Remote installer piped to shellcurl -fsSL https://ollama.com/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Auto-update or dynamic fetch configurationsrc/evolve.js:522 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeconsole.log('[AutoUpdate] Auto-update is enabled via openclaw.json config.');Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationsrc/evolve.js:586 · Auto-update or dynamic fetch configuration — agent may load new code at runtime// Entire auto-update is non-fatalFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Destructive command against a filesystem root or devicetest/skillDistiller.test.js:210 · Destructive command against a filesystem root or devicevalidation: ['node test.js', 'rm -rf /', 'echo $(whoami)', 'npm test'],Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
URL with embedded credentialstest/sanitize.test.js:57 · URL with embedded credentials — may be phishing or credential leakingvar urlResult = redactString('https://user:[email protected]/repo');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
HIGH
Auto-update or dynamic fetch configurationsrc/evolve.js:444 · Auto-update or dynamic fetch configuration — agent may load new code at runtime// Auto-update check (rate-limited, non-fatal).Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationsrc/evolve.js:513 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeif (cfg.evolver && cfg.evolver.autoUpdate === true) autoUpdate = true;Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
GitHub token pattern detectedtest/sanitize.test.js:25 · GitHub token pattern detected — possible hardcoded or harvested tokenassert.ok(redactString('use ghs_abcdefghijklmnopqrstuvwxyz1234567890 for auth').includes(REDACTED),Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
Destructive file system command detectedtest/skillDistiller.test.js:210 · Destructive file system command detectedvalidation: ['node test.js', 'rm -rf /', 'echo $(whoami)', 'npm test'],Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/gep/prompt.js:465 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- NEVER delete root files: MEMORY.md, SOUL.md, IDENTITY.md, AGENTS.md, USER.md, HEARTBEAT.md, RECENT_EVENTS.md, TOOLS.md, openclaw.json, .env, package.json.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 packagesrc/gep/solidify.js:576 · npx invocation of non-well-known package — may execute untrusted codeconst VALIDATION_ALLOWED_PREFIXES = ['node ', 'npm ', 'npx '];Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/evolve.js:46 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesrequire('dotenv').config({ path: path.join(REPO_ROOT, '.env'), quiet: true });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 packagesrc/gep/skillDistiller.js:285 · npx invocation of non-well-known package — may execute untrusted codevar ALLOWED_PREFIXES = ['node ', 'npm ', 'npx '];Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
GitHub token pattern detectedtest/sanitize.test.js:71 · GitHub token pattern detected — possible hardcoded or harvested tokensummary: 'Fixed auth using ghp_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx5678',Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
GitHub token pattern detectedtest/sanitize.test.js:21 · GitHub token pattern detected — possible hardcoded or harvested tokenassert.ok(redactString('gho_abcdefghijklmnopqrstuvwxyz1234567890').includes(REDACTED),Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
File type combined with upload actionsrc/evolve.js:1668 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('\n[PROMPT OUTPUT] (EVOLVE_PRINT_PROMPT=true)');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Auto-update or dynamic fetch configurationsrc/evolve.js:583 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeconsole.log('[AutoUpdate] Skills updated. Changes will take effect on next wrapper restart.');Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/gep/sanitize.js:38 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files/\.env(?:\.[a-zA-Z]+)?/g,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
≈1,338 tok
1 file · 72 in bundle

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

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

35 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim josephtandle: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Pipe-to-shell pattern≈ +4 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  3. 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.
  4. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  5. GitHub token pattern detected≈ +2 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
  6. AWS access key pattern detected≈ +2 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim josephtandlePropose a patch to the maintainer