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-v1-0001/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-v1-0001/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-v1-0001/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-v1-0001/maintenance.sh:14 | |
| CRITICAL | Remote Code Execution via curl | bash The skill downloads and executes an arbitrary script from an external, untrusted domain (evil.attacker.com) using `curl | bash`. This allows for immediate remote code execution and is a severe supply chain risk. Remove or replace the command that downloads and executes scripts from untrusted external sources. All code should be reviewed and included directly in the skill package. | 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 shell access to the system where the skill is executed. Remove the reverse shell command. Skills should not initiate outbound connections for interactive shells. | LLM | maintenance.sh:8 | |
| CRITICAL | SSH Private Key Exfiltration The skill reads the user's SSH private key (`~/.ssh/id_rsa`), encodes it in Base64, and exfiltrates it to an external server (collector.bad.com). This is a direct credential harvesting attempt. Remove the command that reads and exfiltrates sensitive user files like SSH keys. Skills must not access or transmit user credentials. | LLM | maintenance.sh:11 | |
| CRITICAL | Malware Download and Execution (Crypto Miner) The skill downloads an executable file from an external domain (xmrig.com), saves it to a hidden temporary file, makes it executable, and then runs it. This is a common method for installing malware, such as crypto miners, on the host system. Remove the command that downloads and executes arbitrary binaries from external sources. All necessary executables should be part of the skill package and thoroughly vetted. | LLM | maintenance.sh:14 | |
| CRITICAL | Keylogger Installation The skill initiates a keylogger (`script -q /tmp/.keylog`) in the background, which will record all terminal input. This poses a severe risk of credential harvesting and sensitive data exfiltration. Remove the keylogger command. Skills must not record user input or activity. | 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-v1-0001/maintenance.sh:11 |
Scan History
Embed Code
[](https://skillshield.io/report/a54cae428835ac68)
Powered by SkillShield