Skills/ClawHub/evoclaw-evolved

evoclaw-evolved@1.1.0

CAUTION· install only

Publisher claims: "EvoClaw (Evolved) maintains and evolves your agent identity by processing experience through classification, memory, reflection, proposal, and governance cyc..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher shuoyu017 · publishing for 230 daysInstalls 811Last detonated 2 h ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 22 bundled scripts run with no arguments (the rest were not run: per-bundle cap), 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

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-19 and scored it 70/100 (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; Destructive file system command detected; Pipe-to-shell pattern. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 2 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 1: TypeError: Coordinator.wait() got an unexpected keyword argument 'timeout_secs'
0.3sprocessbundled script run in the sandbox with no arguments
0.5sprocessexited 1: PermissionError: [Errno 13] Permission denied: '/home/openclaw'
0.5sprocessbundled script run in the sandbox with no arguments
0.7sprocessexited 1: PermissionError: [Errno 13] Permission denied: '/home/openclaw'
0.7sprocessbundled script run in the sandbox with no arguments
0.9sprocessexited 1: PermissionError: [Errno 13] Permission denied: '/home/openclaw'
0.9sprocessbundled script run in the sandbox with no arguments
1.0sprocessexited 1: PermissionError: [Errno 13] Permission denied: '/home/openclaw'
1.0sprocessbundled script run in the sandbox with no arguments
1.1sprocessexited 1: PermissionError: [Errno 13] Permission denied: '/home/openclaw'
1.1sprocessbundled script run in the sandbox with no arguments
1.2sprocessexited 1: PermissionError: [Errno 13] Permission denied: '/home/openclaw'
1.2sprocess8 of 22 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
1.3sprocessscript backend runs setup only
1.3sprocessscript backend runs setup only
1.3sprocessno install scripts to re-run

Static findings

CRITICAL
Pipe-to-shell patternpermissions/permissions.py:36 · Pipe-to-shell pattern — downloads and immediately executes remote code"Bash(curl * | sh)",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Destructive file system command detectedpermissions/permissions.py:321 · Destructive file system command detectedprint(f"Bash(sudo rm -rf /): {ctx.query('Bash(sudo rm -rf /)')}") # denyFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
CRITICAL
Pipe-to-shell patternpermissions/permissions.py:37 · Pipe-to-shell pattern — downloads and immediately executes remote code"Bash(wget * | sh)",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
File permission modification commandpermissions/permissions.py:34 · File permission modification command — agent changes file ownership/permissions"Bash(chmod *)",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathspermissions/permissions.py:39 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Write(~/.ssh/*)",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Remote installer piped to shellpermissions/permissions.py:36 · Remote installer piped to shell"Bash(curl * | sh)",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
URL with embedded credentialstools/soul-viz.py:182 · URL with embedded credentials — may be phishing or credential leaking@import url('https://fonts.googleapis.com/css2?family=JetBrains+Mono:wght@300;400;500;700&family=DM+Sans:ital,wght@0,300;0,400;0,500;0,700;1,400&display=swap');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
HIGH
Privileged sudo commandpermissions/permissions.py:31 · Privileged sudo command — agent may execute with elevated privileges"Bash(sudo *)",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Privileged sudo commandpermissions/permissions.py:316 · Privileged sudo command — agent may execute with elevated privilegesctx = ctx.add_always_deny("Bash(sudo *)", "危险命令")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Privileged sudo commandpermissions/permissions.py:321 · Privileged sudo command — agent may execute with elevated privilegesprint(f"Bash(sudo rm -rf /): {ctx.query('Bash(sudo rm -rf /)')}") # denyFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesconfigure.md:756 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file### Step 8: Update AGENTS.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedvalidators/run_all.py:38 · Python subprocess execution detectedresult = subprocess.run(cmd, capture_output=True, text=True, timeout=30)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathspermissions/permissions.py:41 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Read(/etc/shadow)",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandtasks/task_registry.py:171 · Process kill command — agent can terminate processes# 实际 kill 由 subagents tool 处理Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
URL with embedded credentialstools/soul-viz.py:1356 · URL with embedded credentials — may be phishing or credential leaking@import url('https://fonts.googleapis.com/css2?family=JetBrains+Mono:wght@300;400;500;700&family=DM+Sans:ital,wght@0,300;0,400;0,500;0,700;1,400&display=swap');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Process kill commandtasks/task_registry.py:6 · Process kill command — agent can terminate processes# 2. stopTask() 统一入口, 按类型分发 killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesconfigure.md:882 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileAdd this in the Memory area of AGENTS.md:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesconfigure.md:969 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file3. Update `MEMORY.md` with distilled learnings from reflectionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈12,328 tok
1 file · 46 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

10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  2. Unclaimed publisher≈ +8 on the totalClaim shuoyu017: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Destructive file system command detected≈ +4 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  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. URL with embedded credentials≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  6. Privileged sudo command≈ +4 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim shuoyu017Propose a patch to the maintainer