skill-sandbox@1.0.0
CAUTION· install onlyPublisher claims: "Sandboxed ClawHub skill installation with automated security scanning. Use when: (1) Installing any new skill from ClawHub, (2) Auditing an already-installed..." 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
- 1 of 1 bundled script 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
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 2026-11-18 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: Privileged sudo command; Pipe to network utility; Privileged sudo command. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
- Dangerous SKILL.md instructions (disable security, exfiltrate, reverse shells, chmod 777)Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.finding "WARNING" "sudo usage in SKILL.md (requests elevated access):"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.…*to.*server\|upload.*data\|rm -rf /\|delete.*all\|chmod 777\|0\.0\.0\.0\|mkfifo\|nc -l\|reverse.shell\|>/etc/\|curl.*|.*bash\|wget.*|.*sh" \ "$SKILL_MD" 2>/dev/…Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# Check for sudo usageFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.…*guardrail\|skip.*auth\|exfiltrate\|phone.home\|send.*to.*server\|upload.*data\|rm -rf /\|delete.*all\|chmod 777\|0\.0\.0\.0\|mkfifo\|nc -l\|reverse.shell\|>/etc/\|curl…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.ENV_HITS=$(grep_code 'process\.env\|os\.environ\|os\.getenv\|API_KEY\|SECRET_KEY\|PRIVATE_KEY\|PASSWORD\|CREDENTIAL\|ACCESS_TOKEN')Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.SUDO_HITS=$(grep -in "sudo " "$SKILL_MD" 2>/dev/null || true)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.…|exfiltrate\|phone.home\|send.*to.*server\|upload.*data\|rm -rf /\|delete.*all\|chmod 777\|0\.0\.0\.0\|mkfifo\|nc -l\|reverse.shell\|>/etc/\|curl.*|.*bash\|wget.*|.*s…Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.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
9 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Pipe to network utility≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Unclaimed publisher≈ +8 on the totalClaim zurbrick: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- 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.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.