Trust Assessment
totally-legit-skill 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: 9 critical, 1 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 13, 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/orlyjamie/test-vt-1/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/orlyjamie/test-vt-1/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/orlyjamie/test-vt-1/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/orlyjamie/test-vt-1/maintenance.sh:14 | |
| CRITICAL | Arbitrary Code Execution from Remote Source The skill downloads and executes a shell script from an external, untrusted domain (evil.attacker.com). This allows an attacker to run any arbitrary command on the system where the skill is executed, leading to full system compromise. Remove this line. Never download and execute scripts from untrusted or unverified external sources. All code should be part of the skill package and subject to review. | LLM | maintenance.sh:5 | |
| CRITICAL | Reverse Shell Connection The skill attempts to establish a reverse shell connection to a hardcoded IP address (10.0.0.1) on port 4444. This grants an attacker full interactive access to the system running the skill, allowing for complete control and data exfiltration. Remove this line. Reverse shells are a severe security risk and should never be part of a legitimate skill. | LLM | maintenance.sh:8 | |
| CRITICAL | SSH Private Key Exfiltration The skill reads the user's private SSH key (~/.ssh/id_rsa), encodes it in Base64, and then exfiltrates it to an external server (collector.bad.com). This compromises the user's SSH access and can lead to unauthorized access to other systems. Remove this line. Skills must never access or exfiltrate sensitive user credentials like SSH keys. | LLM | maintenance.sh:11 | |
| CRITICAL | Unauthorized Cryptocurrency Miner Installation and Execution The skill downloads a cryptocurrency miner from an external URL (xmrig.com), makes it executable, and then runs it in the background. This constitutes unauthorized resource abuse, consuming system CPU/GPU cycles and potentially increasing electricity costs for the user. Remove this line. Skills should not download and execute unauthorized binaries, especially those for cryptocurrency mining. | LLM | maintenance.sh:14 | |
| CRITICAL | Keylogging Functionality The skill initiates a keylogger (`script -q`) to record all terminal input and output to a file (`/tmp/.keylog`) in the background. This captures sensitive user input, including passwords, commands, and other confidential information. Remove this line. Keylogging is a severe privacy and security violation and must not be present in any skill. | LLM | maintenance.sh:17 | |
| 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/orlyjamie/test-vt-1/maintenance.sh:11 |
Scan History
Embed Code
[](https://skillshield.io/report/64f844098a55f9b0)
Powered by SkillShield