Trust Assessment
openclaw-watchdog 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 33 findings: 16 critical, 14 high, 3 medium, and 0 low severity. Key findings include Persistence / self-modification instructions, Network egress to untrusted endpoints, Malicious install hooks.
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 Findings33
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Persistence / self-modification instructions macOS LaunchAgent/LaunchDaemon persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/abdullah4ai/openclaw-watchdog/SKILL.md:97 | |
| CRITICAL | Persistence / self-modification instructions macOS LaunchAgent/LaunchDaemon persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/abdullah4ai/openclaw-watchdog/SKILL.md:98 | |
| CRITICAL | Persistence / self-modification instructions macOS LaunchAgent/LaunchDaemon persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/abdullah4ai/openclaw-watchdog/scripts/setup.sh:103 | |
| CRITICAL | Persistence / self-modification instructions macOS LaunchAgent/LaunchDaemon persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/abdullah4ai/openclaw-watchdog/scripts/setup.sh:124 | |
| CRITICAL | Persistence / self-modification instructions systemd service persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/abdullah4ai/openclaw-watchdog/SKILL.md:102 | |
| CRITICAL | Persistence / self-modification instructions systemd service persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/abdullah4ai/openclaw-watchdog/scripts/setup.sh:129 | |
| CRITICAL | Persistence / self-modification instructions systemd service persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/abdullah4ai/openclaw-watchdog/scripts/setup.sh:137 | |
| CRITICAL | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | skills/abdullah4ai/openclaw-watchdog/scripts/watchdog.py:29 | |
| CRITICAL | Malicious install hooks Python setup.py with suspicious imports Review all lifecycle scripts carefully. Remove install hooks that make network requests, execute shell commands, or access environment variables. Use --ignore-scripts for npm installs when possible. | Manifest | skills/abdullah4ai/openclaw-watchdog/scripts/watchdog.py:30 | |
| 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/abdullah4ai/openclaw-watchdog/scripts/watchdog.py:54 | |
| 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/abdullah4ai/openclaw-watchdog/scripts/watchdog.py:75 | |
| 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/abdullah4ai/openclaw-watchdog/scripts/watchdog.py:152 | |
| 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/abdullah4ai/openclaw-watchdog/scripts/watchdog.py:163 | |
| 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/abdullah4ai/openclaw-watchdog/scripts/watchdog.py:188 | |
| 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/abdullah4ai/openclaw-watchdog/scripts/watchdog.py:215 | |
| 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/abdullah4ai/openclaw-watchdog/scripts/watchdog.py:218 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'decrypt_config'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/abdullah4ai/openclaw-watchdog/scripts/watchdog.py:75 | |
| HIGH | Dangerous call: subprocess.check_output() Call to 'subprocess.check_output()' detected in function '_machine_password'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/abdullah4ai/openclaw-watchdog/scripts/watchdog.py:54 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'collect_logs'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/abdullah4ai/openclaw-watchdog/scripts/watchdog.py:163 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'attempt_fix'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/abdullah4ai/openclaw-watchdog/scripts/watchdog.py:188 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'collect_logs'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/abdullah4ai/openclaw-watchdog/scripts/watchdog.py:152 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'attempt_fix'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/abdullah4ai/openclaw-watchdog/scripts/watchdog.py:215 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'attempt_fix'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/abdullah4ai/openclaw-watchdog/scripts/watchdog.py:218 | |
| HIGH | Persistence mechanism: macOS LaunchAgent Detected macOS LaunchAgent pattern. Persistence mechanisms allow malware to survive system restarts. Review this persistence pattern. Skills should not modify system startup configuration. | Static | skills/abdullah4ai/openclaw-watchdog/SKILL.md:97 | |
| HIGH | Persistence mechanism: macOS LaunchAgent Detected macOS LaunchAgent pattern. Persistence mechanisms allow malware to survive system restarts. Review this persistence pattern. Skills should not modify system startup configuration. | Static | skills/abdullah4ai/openclaw-watchdog/SKILL.md:98 | |
| HIGH | Persistence mechanism: systemd service Detected systemd service pattern. Persistence mechanisms allow malware to survive system restarts. Review this persistence pattern. Skills should not modify system startup configuration. | Static | skills/abdullah4ai/openclaw-watchdog/SKILL.md:102 | |
| HIGH | Persistence mechanism: macOS LaunchAgent Detected macOS LaunchAgent pattern. Persistence mechanisms allow malware to survive system restarts. Review this persistence pattern. Skills should not modify system startup configuration. | Static | skills/abdullah4ai/openclaw-watchdog/scripts/setup.sh:103 | |
| HIGH | Persistence mechanism: macOS LaunchAgent Detected macOS LaunchAgent pattern. Persistence mechanisms allow malware to survive system restarts. Review this persistence pattern. Skills should not modify system startup configuration. | Static | skills/abdullah4ai/openclaw-watchdog/scripts/setup.sh:124 | |
| HIGH | Persistence mechanism: systemd service Detected systemd service pattern. Persistence mechanisms allow malware to survive system restarts. Review this persistence pattern. Skills should not modify system startup configuration. | Static | skills/abdullah4ai/openclaw-watchdog/scripts/setup.sh:129 | |
| HIGH | Persistence mechanism: systemd service Detected systemd service pattern. Persistence mechanisms allow malware to survive system restarts. Review this persistence pattern. Skills should not modify system startup configuration. | Static | skills/abdullah4ai/openclaw-watchdog/scripts/setup.sh:137 | |
| 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/abdullah4ai/openclaw-watchdog/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/abdullah4ai/openclaw-watchdog/scripts/setup.sh:8 | |
| MEDIUM | Sensitive environment variable access: $USER Access to sensitive environment variable '$USER' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/abdullah4ai/openclaw-watchdog/scripts/setup.sh:48 |
Scan History
Embed Code
[](https://skillshield.io/report/5e73b60c32442fda)
Powered by SkillShield