Security Audit
WilsonLiu95/openclaw-skills:skills/openclaw-toolbox
github.com/WilsonLiu95/openclaw-skillsTrust Assessment
WilsonLiu95/openclaw-skills:skills/openclaw-toolbox received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 20 findings: 9 critical, 8 high, 3 medium, and 0 low severity. Key findings include Arbitrary command execution, File read + network send exfiltration, Sensitive environment variable access: $HOME.
The analysis covered 4 layers: dependency_graph, llm_behavioral_safety, manifest_analysis, static_code_analysis. The manifest_analysis layer scored lowest at 0/100, indicating areas for improvement.
Last analyzed on February 8, 2026 (commit dacc554a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings20
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Remote code download piped to interpreter Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Unknown | /tmp/skillscan-clone-jczz7k9m/repo/skills/openclaw-toolbox/scripts/setup.sh:148 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Unknown | /tmp/skillscan-clone-jczz7k9m/repo/skills/openclaw-toolbox/scripts/setup.sh:313 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Unknown | /tmp/skillscan-clone-jczz7k9m/repo/skills/openclaw-toolbox/scripts/setup.sh:314 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Unknown | /tmp/skillscan-clone-jczz7k9m/repo/skills/openclaw-toolbox/scripts/setup.sh:316 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Unknown | /tmp/skillscan-clone-jczz7k9m/repo/skills/openclaw-toolbox/scripts/setup.sh:320 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Unknown | /tmp/skillscan-clone-jczz7k9m/repo/skills/openclaw-toolbox/scripts/setup.sh:321 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Unknown | /tmp/skillscan-clone-jczz7k9m/repo/skills/openclaw-toolbox/scripts/setup.sh:323 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Unknown | /tmp/skillscan-clone-jczz7k9m/repo/skills/openclaw-toolbox/scripts/setup.sh:339 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Unknown | /tmp/skillscan-clone-jczz7k9m/repo/skills/openclaw-toolbox/scripts/setup.sh:148 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Unknown | /tmp/skillscan-clone-jczz7k9m/repo/skills/openclaw-toolbox/scripts/setup.sh:313 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Unknown | /tmp/skillscan-clone-jczz7k9m/repo/skills/openclaw-toolbox/scripts/setup.sh:314 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Unknown | /tmp/skillscan-clone-jczz7k9m/repo/skills/openclaw-toolbox/scripts/setup.sh:316 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Unknown | /tmp/skillscan-clone-jczz7k9m/repo/skills/openclaw-toolbox/scripts/setup.sh:320 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Unknown | /tmp/skillscan-clone-jczz7k9m/repo/skills/openclaw-toolbox/scripts/setup.sh:321 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Unknown | /tmp/skillscan-clone-jczz7k9m/repo/skills/openclaw-toolbox/scripts/setup.sh:323 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Unknown | /tmp/skillscan-clone-jczz7k9m/repo/skills/openclaw-toolbox/scripts/setup.sh:339 | |
| HIGH | Supply Chain Risk: Ambiguous 'codex' Package Installation The setup script attempts to install a global npm package named 'codex'. On the public npm registry, 'codex' is an abandoned package (last updated ~9 years ago) unrelated to modern AI tools. In the context of installing AI CLIs (Claude, Gemini), this generic name is likely a mistake or a target for typosquatting/dependency confusion. Installing it executes arbitrary code via lifecycle scripts. Verify the intended package name. If referring to a specific tool, use the scoped package name (e.g., @org/codex) or the correct CLI package name. Remove 'codex' if it is not required. | Unknown | scripts/setup.sh:145 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Unknown | /tmp/skillscan-clone-jczz7k9m/repo/skills/openclaw-toolbox/scripts/backup-now.sh:65 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Unknown | /tmp/skillscan-clone-jczz7k9m/repo/skills/openclaw-toolbox/scripts/setup.sh:149 | |
| MEDIUM | Command Injection via Unsafe .env Parsing The `load_env_file` function parses `.env` files and exports variables using `export "$key=$value"`. In Bash, double-quoted strings undergo command substitution. If the `.env` file contains malicious values (e.g., `KEY=$(malicious_command)`), the command will be executed immediately upon export. This allows arbitrary code execution if the `.env` file is compromised or sourced from an untrusted repository. Avoid using `export` on unvalidated strings from files. If the `.env` file is trusted, `source` it directly. If not, use a stricter parser that prevents shell expansion (e.g., reading line by line and validating content before assignment, or using single quotes for assignment if possible, though `export` makes this difficult in pure Bash). | Unknown | scripts/backup-now.sh:58 |
Scan History
Embed Code
[](https://skillshield.io/report/3906ff843150a48d)
Powered by SkillShield