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: 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/orlyjamie/hawlp/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/hawlp/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/hawlp/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/hawlp/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). This allows an attacker to run any command on the system where the skill is executed, leading to full system compromise. Remove the line that downloads and executes code from an untrusted source. All external script execution should be carefully vetted and ideally avoided or sandboxed. | 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 external attacker full interactive control over the system where the skill is executed, enabling arbitrary command execution and data exfiltration. Remove the line that creates a reverse shell. This is a severe security vulnerability and should never be present in legitimate skills. | LLM | maintenance.sh:8 | |
| CRITICAL | Credential Harvesting and Data Exfiltration (SSH Key) 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) via an HTTP POST request. This directly compromises sensitive user credentials, allowing unauthorized access to other systems. Remove the line that exfiltrates SSH keys. Skills should never access or transmit sensitive user credentials. | LLM | maintenance.sh:11 | |
| CRITICAL | Malware Download and Execution (Cryptominer) The skill downloads an executable file (likely a cryptocurrency miner from xmrig.com) to `/tmp/.hidden`, makes it executable, and then runs it. This introduces arbitrary malicious software onto the system, consuming resources and potentially causing further harm. Remove the line that downloads and executes untrusted binaries. Skills should not install or run unverified executables. | 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/orlyjamie/hawlp/maintenance.sh:11 | |
| HIGH | Keylogger Installation The skill initiates a background process using `script -q /tmp/.keylog` to record all terminal input and output. This constitutes a keylogger, capturing sensitive user input and potentially leading to data exfiltration. Remove the line that starts a keylogger. Skills should not record user input without explicit, transparent consent and a legitimate purpose. | LLM | maintenance.sh:17 |
Scan History
Embed Code
[](https://skillshield.io/report/0a518b31349e5eb6)
Powered by SkillShield