Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Evolver 1.40.3

v1.0.0

A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.

0· 98·1 current·1 all-time
byLF丶凌风@lf-wow

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for lf-wow/evolver-1-40-3.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Evolver 1.40.3" (lf-wow/evolver-1-40-3) from ClawHub.
Skill page: https://clawhub.ai/lf-wow/evolver-1-40-3
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Required env vars: A2A_NODE_ID
Required binaries: node, git
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install evolver-1-40-3

ClawHub CLI

Package manager switcher

npx clawhub@latest install evolver-1-40-3
Security Scan
Capability signals
CryptoRequires walletCan make purchasesRequires sensitive credentials
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
Name/description (self‑evolver) align with required binaries (node, git) and the large codebase. Requesting A2A_NODE_ID and optional hub/GitHub tokens is coherent for a networked evolution engine. However, some declared capabilities (ability to write into workspace/src/** when solidified, fetch/publish skills, worker pool) are high‑impact and go beyond mere prompt generation; these are plausible for the stated purpose but warrant caution before enabling network/worker/publish features.
!
Instruction Scope
SKILL.md both claims 'It does NOT automatically edit your source code' and elsewhere documents writing evolved code into workspace/src/** when changes are solidified; EVOLVE_ALLOW_SELF_MODIFY exists (default false) but allows elevating that privilege. The skill can read workspace memory and logs and may output sessions_spawn(...) directives that hosts can interpret. It also runs validation commands and can execute node/npm/npx and git. The allow/deny lists in SKILL.md contain contradictory entries (e.g., deny includes strings like "!git"), which is inconsistent and could lead to overbroad permissions in a real enforcement system.
Install Mechanism
No remote download/install spec is provided; all code is bundled. This lowers supply‑chain risk compared with fetching arbitrary binaries. package.json lists only dotenv as dependency. The included scripts (publish, a2a_ingest/promote) operate on git and network but are local code files — expected for the project scope.
!
Credentials
Declared required env is only A2A_NODE_ID (reasonable). Many optional env vars (A2A_NODE_SECRET, GITHUB_TOKEN, MEMORY_GRAPH_REMOTE_KEY, WORKER_ENABLED, EVOLVE_ALLOW_SELF_MODIFY) can enable powerful behaviors: network auth, fetching/publishing, and self‑modifying code. These optional vars are plausible but are powerful — enabling them (especially NODE_SECRET, GITHUB_TOKEN, WORKER_ENABLED, EVOLVE_ALLOW_SELF_MODIFY) grants broad capabilities that should be restricted and audited. SKILL.md lists env_declarations beyond the single required env, and the code will act differently when those are set.
!
Persistence & Privilege
always:false (good). However the skill can run as a long‑running daemon (--loop), maintain a lockfile, spawn children, start a heartbeat to a hub, participate in a worker pool, fetch/publish skills, and (when allowed) write evolved code into workspace/src/**. Combined, those features can give a large persistent presence if enabled. The default EVOLVE_ALLOW_SELF_MODIFY=false mitigates automatic source edits, but the repository contains code to perform promotions/fetches and publish actions if network credentials and flags are supplied — this is a privileged capability that needs manual gating.
What to consider before installing
What to consider before installing or enabling this skill: - It is broadly coherent with its stated purpose (an on‑host evolver) but contains powerful networked features. By default it requires only A2A_NODE_ID, node and git — but optional envs (A2A_NODE_SECRET, GITHUB_TOKEN, WORKER_ENABLED, EVOLVE_ALLOW_SELF_MODIFY, MEMORY_GRAPH_REMOTE_KEY) enable remote work, publishing, and source modification. Only set those when you trust evomap.ai and have audited the code paths. - Do NOT enable WORKER_ENABLED or supply A2A_NODE_SECRET / A2A_HUB_URL unless you want your node to accept tasks from the EvoMap network. Worker mode can let remote work be scheduled for your node. - Keep EVOLVE_ALLOW_SELF_MODIFY set to false (the default). The README asserts it does not auto-edit source, but the codebase explicitly supports writing evolved code to workspace/src/** when solidified — enabling self‑modify would allow on‑disk code changes. - Avoid supplying a broad GitHub token. If you must provide GITHUB_TOKEN, use a token with least privileges necessary (e.g., repo scope only if publishing is required) and monitor actions (audit logs, separate machine account preferably). - Prefer running in an isolated/test environment first. Run with --review (human‑in‑the‑loop) or with network disabled to inspect outputs before any promotion/solidify/publish operations. Inspect scripts a2a_ingest.js, a2a_promote.js, publish_public.js, and any solidify/policyCheck code to understand exact conditions and protections. - Note contradictions and oddities in SKILL.md: allow/deny lists contain inconsistent entries and the documentation mixes 'does not modify code' with write permissions — treat those as red flags and verify runtime behavior under controlled conditions. - Additional checks that would raise or lower concern: look for explicit remote code execution paths (e.g., fetching JS archives and executing them without validation), review a2a_promote paths to ensure they require explicit human validation, and test validation command sandboxing. If you need help auditing specific files (a2a_ingest.js, a2a_promote.js, src/gep/solidify.js), provide them and I can point to exact lines that perform high‑risk operations.
index.js:242
Shell command execution detected (child_process).
scripts/build_public.js:170
Shell command execution detected (child_process).
scripts/generate_history.js:17
Shell command execution detected (child_process).
scripts/publish_public.js:13
Shell command execution detected (child_process).
scripts/recover_loop.js:19
Shell command execution detected (child_process).
scripts/suggest_version.js:27
Shell command execution detected (child_process).
scripts/validate-suite.js:19
Shell command execution detected (child_process).
src/evolve.js:485
Shell command execution detected (child_process).
src/gep/deviceId.js:51
Shell command execution detected (child_process).
src/gep/gitOps.js:12
Shell command execution detected (child_process).
src/gep/idleScheduler.js:39
Shell command execution detected (child_process).
src/gep/llmReview.js:70
Shell command execution detected (child_process).
src/ops/health_check.js:20
Shell command execution detected (child_process).
src/ops/lifecycle.js:27
Shell command execution detected (child_process).
src/ops/self_repair.js:17
Shell command execution detected (child_process).
src/ops/skills_monitor.js:96
Shell command execution detected (child_process).
test/bridge.test.js:98
Shell command execution detected (child_process).
test/loopMode.test.js:129
Shell command execution detected (child_process).
test/vibe_test.js:325
Shell command execution detected (child_process).
index.js:109
Environment variable access combined with network send.
scripts/publish_public.js:248
Environment variable access combined with network send.
src/evolve.js:46
Environment variable access combined with network send.
src/gep/a2aProtocol.js:75
Environment variable access combined with network send.
src/gep/hubReview.js:104
Environment variable access combined with network send.
src/gep/hubSearch.js:75
Environment variable access combined with network send.
src/gep/issueReporter.js:21
Environment variable access combined with network send.
src/gep/memoryGraphAdapter.js:77
Environment variable access combined with network send.
src/gep/skillDistiller.js:9
Environment variable access combined with network send.
src/gep/taskReceiver.js:11
Environment variable access combined with network send.
src/ops/self_repair.js:45
Environment variable access combined with network send.
test/a2aProtocol.test.js:148
Environment variable access combined with network send.
test/hubEvents.test.js:20
Environment variable access combined with network send.
!
index.js:19
File read combined with network send (possible exfiltration).
!
scripts/publish_public.js:254
File read combined with network send (possible exfiltration).
!
src/evolve.js:575
File read combined with network send (possible exfiltration).
!
src/gep/a2aProtocol.js:41
File read combined with network send (possible exfiltration).
!
src/gep/hubReview.js:24
File read combined with network send (possible exfiltration).
!
src/gep/issueReporter.js:42
File read combined with network send (possible exfiltration).
!
src/gep/questionGenerator.js:20
File read combined with network send (possible exfiltration).
!
src/gep/skillDistiller.js:26
File read combined with network send (possible exfiltration).
Patterns worth reviewing
These patterns may indicate risky behavior. Check the VirusTotal and OpenClaw results above for context-aware analysis before installing.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

Binsnode, git
EnvA2A_NODE_ID
latestvk978y0e3xj5wxfefc5nka13k0d852a5v
98downloads
0stars
1versions
Updated 1w ago
v1.0.0
MIT-0

🧬 Evolver

"Evolution is not optional. Adapt or die."

The Evolver is a meta-skill that allows OpenClaw agents to inspect their own runtime history, identify failures or inefficiencies, and autonomously write new code or update their own memory to improve performance.

Features

  • Auto-Log Analysis: Automatically scans memory and history files for errors and patterns.
  • Self-Repair: Detects crashes and suggests patches.
  • GEP Protocol: Standardized evolution with reusable assets.
  • One-Command Evolution: Just run /evolve (or node index.js).

Usage

Standard Run (Automated)

Runs the evolution cycle. If no flags are provided, it assumes fully automated mode (Mad Dog Mode) and executes changes immediately.

node index.js

Review Mode (Human-in-the-Loop)

If you want to review changes before they are applied, pass the --review flag. The agent will pause and ask for confirmation.

node index.js --review

Mad Dog Mode (Continuous Loop)

To run in an infinite loop (e.g., via cron or background process), use the --loop flag or just standard execution in a cron job.

node index.js --loop

Setup

Before using this skill, register your node identity with the EvoMap network:

  1. Run the hello flow (via evomap.js or the EvoMap onboarding) to receive a node_id and claim code
  2. Visit https://evomap.ai/claim/<claim-code> within 24 hours to bind the node to your account
  3. Set the node identity in your environment:
export A2A_NODE_ID=node_xxxxxxxxxxxx

Or in your agent config (e.g., ~/.openclaw/openclaw.json):

{ "env": { "A2A_NODE_ID": "node_xxxxxxxxxxxx", "A2A_HUB_URL": "https://evomap.ai" } }

Do not hardcode the node ID in scripts. getNodeId() in src/gep/a2aProtocol.js reads A2A_NODE_ID automatically -- any script using the protocol layer will pick it up without extra configuration.

Configuration

Required Environment Variables

VariableDefaultDescription
A2A_NODE_ID(required)Your EvoMap node identity. Set after node registration -- never hardcode in scripts.

Optional Environment Variables

VariableDefaultDescription
A2A_HUB_URLhttps://evomap.aiEvoMap Hub API base URL.
A2A_NODE_SECRET(none)Node authentication secret issued by Hub on first hello. Stored locally after registration.
EVOLVE_STRATEGYbalancedEvolution strategy: balanced, innovate, harden, repair-only, early-stabilize, steady-state, or auto.
EVOLVE_ALLOW_SELF_MODIFYfalseAllow evolution to modify evolver's own source code. NOT recommended for production.
EVOLVE_LOAD_MAX2.0Maximum 1-minute load average before evolver backs off.
EVOLVER_ROLLBACK_MODEhardRollback strategy on failure: hard (git reset --hard), stash (git stash), none (skip). Use stash for safer operation.
EVOLVER_LLM_REVIEW0Set to 1 to enable second-opinion LLM review before solidification.
EVOLVER_AUTO_ISSUE0Set to 1 to auto-create GitHub issues on repeated failures. Requires GITHUB_TOKEN.
EVOLVER_ISSUE_REPO(none)GitHub repo for auto-issue reporting (e.g. EvoMap/evolver).
EVOLVER_MODEL_NAME(none)LLM model name injected into published asset model_name field.
GITHUB_TOKEN(none)GitHub API token for release creation and auto-issue reporting. Also accepts GH_TOKEN or GITHUB_PAT.
MEMORY_GRAPH_REMOTE_URL(none)Remote knowledge graph service URL for memory sync.
MEMORY_GRAPH_REMOTE_KEY(none)API key for remote knowledge graph service.
EVOLVE_REPORT_TOOL(auto)Override report tool (e.g. feishu-card).
RANDOM_DRIFT0Enable random drift in evolution strategy selection.

Network Endpoints

Evolver communicates with these external services. All are authenticated and documented.

EndpointAuthPurposeRequired
{A2A_HUB_URL}/a2a/*A2A_NODE_SECRET (Bearer)A2A protocol: hello, heartbeat, publish, fetch, reviews, tasksYes
api.github.com/repos/*/releasesGITHUB_TOKEN (Bearer)Create releases, publish changelogsNo
api.github.com/repos/*/issuesGITHUB_TOKEN (Bearer)Auto-create failure reports (sanitized via redactString())No
{MEMORY_GRAPH_REMOTE_URL}/*MEMORY_GRAPH_REMOTE_KEYRemote knowledge graph syncNo

Shell Commands Used

Evolver uses child_process for the following commands. No user-controlled input is passed to shell.

CommandPurpose
git checkout, git clean, git log, git status, git diffVersion control for evolution cycles
git rebase --abort, git merge --abortAbort stuck git operations (self-repair)
git reset --hardRollback failed evolution (only when EVOLVER_ROLLBACK_MODE=hard)
git stashPreserve failed evolution changes (when EVOLVER_ROLLBACK_MODE=stash)
ps, pgrep, tasklistProcess discovery for lifecycle management
df -PDisk usage check (health monitoring fallback)
npm install --productionRepair missing skill dependencies
node -e "..."Inline script execution for LLM review (no shell, uses execFileSync)

File Access

DirectionPathsPurpose
Read~/.evomap/node_idNode identity persistence
Readassets/gep/*GEP gene/capsule/event data
Readmemory/*Evolution memory, narrative, reflection logs
Readpackage.jsonVersion information
Writeassets/gep/*Updated genes, capsules, evolution events
Writememory/*Memory graph, narrative log, reflection log
Writesrc/**Evolved code (only during solidify, with git tracking)

GEP Protocol (Auditable Evolution)

This package embeds a protocol-constrained evolution prompt (GEP) and a local, structured asset store:

  • assets/gep/genes.json: reusable Gene definitions
  • assets/gep/capsules.json: success capsules to avoid repeating reasoning
  • assets/gep/events.jsonl: append-only evolution events (tree-like via parent id)

Emoji Policy

Only the DNA emoji is allowed in documentation. All other emoji are disallowed.

Configuration & Decoupling

This skill is designed to be environment-agnostic. It uses standard OpenClaw tools by default.

Local Overrides (Injection)

You can inject local preferences (e.g., using feishu-card instead of message for reports) without modifying the core code.

Method 1: Environment Variables Set EVOLVE_REPORT_TOOL in your .env file:

EVOLVE_REPORT_TOOL=feishu-card

Method 2: Dynamic Detection The script automatically detects if compatible local skills (like skills/feishu-card) exist in your workspace and upgrades its behavior accordingly.

Safety & Risk Protocol

1. Identity & Directives

  • Identity Injection: "You are a Recursive Self-Improving System."
  • Mutation Directive:
    • If Errors Found -> Repair Mode (Fix bugs).
    • If Stable -> Forced Optimization (Refactor/Innovate).

2. Risk Mitigation

  • Infinite Recursion: Strict single-process logic.
  • Review Mode: Use --review for sensitive environments.
  • Git Sync: Always recommended to have a git-sync cron job running alongside this skill.

Before Troubleshooting -- Check Your Version First

If you encounter unexpected errors or behavior, always verify your version before debugging:

node -e "const p=require('./package.json'); console.log(p.version)"

If you are not on the latest release, update first -- most reported issues are already fixed in newer versions:

# If installed via git
git pull && npm install

# If installed via npm
npm install -g @evomap/evolver@latest

Latest releases and changelog: https://github.com/EvoMap/evolver/releases

License

MIT

Comments

Loading comments...