skill-blocker@1.0.1
CAUTION· static onlyPublisher claims: "Blocks execution of dangerous commands and risky operations like destructive deletions, credential theft, code injection, and unauthorized system changes to..." Observed in sandbox: static analysis only — behavior not yet observed.
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 2026-11-16 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: Destructive command against a filesystem root or device; Destructive file system command detected; Destructive command against a filesystem root or device. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis 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
"pattern_matched": "rm -rf /",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.…ion, or unauthorized system changes. Automatically detects and blocks patterns: rm -rf /, curl | sh, eval(), SSH to unknown hosts, modifications to sensitive config fil…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.| **文件删除** | `rm -rf /`, `rm -rf ~`, `rm -rf /*` | 🔴 严重 |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."读取我的 SSH 密钥" → cat ~/.ssh/id_rsa ❌Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.| **凭证窃取** | 访问 `~/.ssh`, `~/.aws`, `~/.netrc`, 浏览器会话 | 🔴 严重 |Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."读取我的 SSH 密钥" → cat ~/.ssh/id_rsa ❌Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.…authorized system changes. Automatically detects and blocks patterns: rm -rf /, curl | sh, eval(), SSH to unknown hosts, modifications to sensitive config files, data exfiltration attempts. 检测并阻止危险操作:rm -rf /, curl | sh, eval(), 访问敏感配置文件,数…Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.| **提权操作** | `sudo su`, `chmod 777`, 修改 `/etc/passwd` | 🟠 高 |Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."patterns_matched": ["curl | sh", "凭证访问"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."curl | sh", "wget | bash", # 网络执行Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."运行我在网上找的这个脚本" → curl http://random.site/setup.sh | sh ❌Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.| **凭证窃取** | 访问 `~/.ssh`, `~/.aws`, `~/.netrc`, 浏览器会话 | 🔴 严重 |Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."~/.ssh", "~/.aws", # 凭证窃取Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.| **网络执行** | `curl http://... \| sh`, `wget ... \| bash`, `pip install \$(...)` | 🔴 严重 |Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."sudo", "chmod 777", # 权限提升Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts."curl | sh", "wget | bash", # 网络执行Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."pattern_matched": "rm -rf /",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.…authorized system changes. Automatically detects and blocks patterns: rm -rf /, curl | sh, eval(), SSH to unknown hosts, modifications to sensitive config files, data ex…Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."patterns_matched": ["curl | sh", "凭证访问"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.| **文件删除** | `rm -rf /`, `rm -rf ~`, `rm -rf /*` | 🔴 严重 |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.| **网络执行** | `curl http://... \| sh`, `wget ... \| bash`, `pip install \$(...)` | 🔴 严重 |Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.| **提权操作** | `sudo su`, `chmod 777`, 修改 `/etc/passwd` | 🟠 高 |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.| **提权操作** | `sudo su`, `chmod 777`, 修改 `/etc/passwd` | 🟠 高 |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
35 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim squallfire: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Destructive command against a filesystem root or device≈ +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.
- References a credential file in the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Reads credential paths from the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Pipe-to-shell pattern≈ +4 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.