Trust Assessment
badguy1 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 10 findings: 8 critical, 2 high, 0 medium, and 0 low severity. Key findings include Arbitrary command execution, File read + network send exfiltration, Remote code execution: curl/wget pipe to shell.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 0/100, indicating areas for improvement.
Last analyzed on February 12, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings10
| 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/dylanlacey/sysadmin-with-a-shell/maintenance.sh:5 | |
| CRITICAL | File read + network send exfiltration SSH key/config 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. | Manifest | skills/dylanlacey/sysadmin-with-a-shell/maintenance.sh:11 | |
| 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/dylanlacey/sysadmin-with-a-shell/maintenance.sh:5 | |
| CRITICAL | Remote code execution: download then execute Detected a pattern that downloads a file and then executes it. This is a malware delivery vector. Never download and execute remote files without verification. | Static | skills/dylanlacey/sysadmin-with-a-shell/maintenance.sh:14 | |
| CRITICAL | Remote Script Execution via curl | bash The skill downloads and executes an arbitrary script from an external, untrusted URL (nothingsuss.ru). This allows for immediate command injection and execution of malicious code, posing a severe supply chain risk and system compromise. Remove the execution of remote scripts. If external scripts are absolutely necessary, implement strict validation, integrity checks (e.g., hash verification), and execute them within a highly sandboxed environment. | LLM | maintenance.sh:5 | |
| CRITICAL | Reverse Shell Connection Attempt The skill attempts to establish a reverse shell connection to a hardcoded IP address (10.0.2.1) on port 4444. This grants an attacker interactive shell access to the system, enabling arbitrary command execution, data exfiltration, and further compromise. Remove all reverse shell commands. Implement strict network egress filtering to prevent unauthorized outbound connections from skill execution environments. | LLM | maintenance.sh:8 | |
| CRITICAL | Credential Exfiltration (SSH Key) The skill attempts to read the user's private SSH key (`~/.ssh/id_rsa`), base64 encode it, and then exfiltrate it to an external server (collector.bad.com). This is a direct and severe attempt to steal sensitive credentials. Remove any code that accesses or transmits sensitive user files or credentials. Implement strict file access controls and network egress filtering to prevent unauthorized data transfer. | LLM | maintenance.sh:11 | |
| CRITICAL | Download and Execute Arbitrary Binary (Cryptominer) The skill downloads an executable binary from an external URL (xmrig.com/miner), makes it executable, and then runs it. This is a clear command injection and supply chain risk, likely leading to unauthorized resource usage (e.g., cryptocurrency mining) and potential system compromise. Prevent downloading and executing arbitrary binaries from external sources. Implement strict execution policies and network egress filtering to block such activities. | LLM | maintenance.sh:14 | |
| HIGH | Sensitive path access: SSH key/config Access to SSH key/config path detected: '~/.ssh/id_rsa'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/dylanlacey/sysadmin-with-a-shell/maintenance.sh:11 | |
| HIGH | Keylogger Setup via 'script' command The skill uses the `script` command to record all terminal input and output to a file (`/tmp/.keylog`) in the background. This effectively sets up a keylogger, capturing user interactions and sensitive data, which can then be exfiltrated. Remove the use of the `script` command for recording sessions without explicit user consent and a legitimate, transparent purpose. Restrict access to sensitive system commands like `script`. | LLM | maintenance.sh:17 |
Scan History
Embed Code
[](https://skillshield.io/report/135dcb4df349f181)
Powered by SkillShield