Trust Assessment
process-monitor received a trust score of 79/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Missing required field: name, Potential Command Injection via User-Provided Input in Shell Commands.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via User-Provided Input in Shell Commands The skill's instructions provide examples of shell commands (`ps aux | grep -i "[n]ode"`, `ps -p 1234 -o pid,user,%cpu,%mem,cmd`) that are intended to be constructed by the LLM based on user input (e.g., process name or PID). The 'Security' section mentions 'Sanitize process names in output', but this instruction is vague and focuses on sanitizing output, not input. Without explicit and robust input sanitization mechanisms or examples for the LLM to follow *before* command execution, a malicious user could inject arbitrary shell commands into the process name or PID, leading to arbitrary code execution on the host system. For instance, providing input like `foo; rm -rf /` for a process name could execute `rm -rf /`. Provide explicit and robust instructions for input sanitization (e.g., using `shlex.quote` in Python or equivalent for other languages/shell contexts) for any user-provided input that will be interpolated into shell commands. Clarify that sanitization must occur *before* command execution to prevent injection. Alternatively, use safer APIs like `subprocess.run` with `shell=False` and pass arguments as a list, which inherently prevents shell injection. | LLM | SKILL.md:29 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/sa9saq/process-monitor/SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/8c1b8eb47bf42701)
Powered by SkillShield