Trust Assessment
openclaw-skill-scanner 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 9 findings: 6 critical, 1 high, 2 medium, and 0 low severity. Key findings include Arbitrary command execution, Missing required field: name, Dangerous call: subprocess.run().
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, indicating areas for improvement.
Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings9
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) 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. | Manifest | skills/epwhesq/openclaw-skill-scanner/scanner.py:126 | |
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) 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. | Manifest | skills/epwhesq/openclaw-skill-scanner/scanner.py:793 | |
| CRITICAL | Arbitrary command execution Python dynamic code execution (exec/eval/compile) 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. | Manifest | skills/epwhesq/openclaw-skill-scanner/scanner.py:118 | |
| CRITICAL | Arbitrary command execution Python dynamic code execution (exec/eval/compile) 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. | Manifest | skills/epwhesq/openclaw-skill-scanner/scanner.py:253 | |
| 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. | Manifest | skills/epwhesq/openclaw-skill-scanner/scanner.py:98 | |
| CRITICAL | Shell command injection via skill slug in blacklist check The `install-hook.sh` script directly interpolates the user-provided `SLUG` variable into a Python command executed via `python3 -c`. A malicious `SLUG` value containing single quotes can break out of the Python string literal, allowing an attacker to inject and execute arbitrary Python code, which in turn can execute shell commands. The `2>/dev/null || true` suppresses errors, potentially hiding the injection attempt. To prevent command injection, avoid direct string interpolation of user-controlled input into shell commands, especially when executing `python3 -c`. Instead, pass the `SLUG` value as a command-line argument to the Python script (e.g., `python3 -c '...' "$SLUG"`) and access it via `sys.argv`, or pass it as an environment variable and access it via `os.environ`. The Python script should then parse this input securely without re-evaluating it as code. | LLM | install-hook.sh:74 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'pre_install_scan'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/epwhesq/openclaw-skill-scanner/scanner.py:793 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/epwhesq/openclaw-skill-scanner/SKILL.md:1 | |
| 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. | Static | skills/epwhesq/openclaw-skill-scanner/install-hook.sh:19 |
Scan History
Embed Code
[](https://skillshield.io/report/4d910e49b21d6ae1)
Powered by SkillShield