skillscout@0.1.0
CAUTION· install onlyPublisher claims: "Find and evaluate OpenClaw AI skills by trust score and security reviews before installation or recommendation." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 8 of 9 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 2026-11-21 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive file system command detected; 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 · 0 s · 2 scenarios · 0 deviationsStatic findings
"details": "cooldown.sh uses eval \"$COMMAND\" with unquoted variable. Attacker can inject shell commands via COMMAND parameter. e.g., COMMAND='true; rm -rf /' would execute."Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."subprocess.run() in orchestrator.py calls execute_financial_analyst() and execute_notification_agent() (simulated)"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."Credential storage in .env file",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.npx @skillscout/mcpFix: Pin versions and sources; vendor anything fetched at install time."details": "No encryption for SQLite database or .env file. Credentials are stored in plaintext."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- Before running `npx clawhub@latest install <skill>`Fix: Pin versions and sources; vendor anything fetched at install time."Restrict ~/.clawdbot/events/ directory to user-only permissions (chmod 700)",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts."python3 subprocess.run() for sessions_spawn integration"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."details": "cooldown.sh uses eval \"$COMMAND\" with unquoted variable. Attacker can inject shell commands via COMMAND parameter. e.g., COMMAND='true; rm -rf /' would execute."Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."subprocess.run(['node', str(script_path)], timeout=60)",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."finding": "API keys for OpenAI/LiteLLM stored in .env file; no authentication between local API server and clients (port 8000, localhost only but no auth token required)."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.".env file (credentials)",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."finding": "Password stored in /home/eth3rnit3/clawd/.env (plaintext); API authentication via JWT cookie. Risk: credential exposure in .env file or cookies."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."Executes arbitrary scripts via subprocess.run()",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."Restrict memory/diary/ directory permissions to user-only (chmod 700)",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts."subprocess.run(['python3', str(script_path)], timeout=60) in workflow_engine.py",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."installCommand": "npx clawhub@latest install rationality",Fix: Pin versions and sources; vendor anything fetched at install time."Add timeout for workflow execution with kill of hung processes",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."finding": "API key stored in plaintext in config files (~/.config/4claw/credentials.json). Thread content fetched includes full post text by default. No encryption in transit mentioned."Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.… "OAuth token stored in plaintext at ~/.openclaw/agents/main/agent/auth-profiles.json. API responses contain quota information for all models. Script output includes model names and reset times." }, "denialOfService"…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.install: `npx clawhub@latest install ${s.author}/${s.name}`,Fix: Pin versions and sources; vendor anything fetched at install time."curl -s -c /tmp/alexandrie_cookies.txt -X POST",Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.`Install: \`npx clawhub@latest install ${s.name}\``Fix: Pin versions and sources; vendor anything fetched at install time.install: `npx clawhub@latest install ${s.author}/${s.name}`,Fix: Pin versions and sources; vendor anything fetched at install time.Cost to the agent
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
12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Destructive command against a filesystem root or device≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Unclaimed publisher≈ +8 on the totalClaim nashbot67: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- 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.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.