Trust Assessment
log-tail received a trust score of 83/100, 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 Potential Command Injection via `journalctl` arguments, Broad access to system logs via `journalctl`.
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 `journalctl` arguments The skill's manifest indicates it requires the `journalctl` binary, and the `SKILL.md` documentation describes usage where user-provided input (e.g., `<service>` for the `--unit` argument) is expected. If the AI agent directly interpolates untrusted user input into a shell command for `journalctl` without proper sanitization or escaping, it could lead to command injection. An attacker could provide malicious input like `my_service; rm -rf /` to execute arbitrary commands on the host system. Ensure that all user-provided arguments for `journalctl` (especially `--unit`) are strictly validated and properly escaped before being passed to the shell. Prefer using command execution methods that pass arguments as a list (e.g., `subprocess.run(['journalctl', '--unit', user_input])` in Python) to avoid shell interpretation of user input. | LLM | SKILL.md:10 | |
| MEDIUM | Broad access to system logs via `journalctl` The skill provides access to `journalctl`, a utility that can read all system logs. While `journalctl` is a legitimate system tool, granting an AI agent unrestricted access to potentially sensitive system logs (which may contain credentials, internal network details, or other confidential information) poses an information disclosure risk. An attacker could prompt the agent to retrieve logs containing sensitive data. Evaluate if the AI agent truly requires access to *all* system logs. Consider implementing stricter filtering or scope limitations for `journalctl` commands (e.g., only allowing specific units, or filtering output for sensitive patterns). Implement data masking or redaction for sensitive information if logs are frequently accessed. Educate users about the potential for sensitive data in logs. | LLM | SKILL.md:10 |
Scan History
Embed Code
[](https://skillshield.io/report/53e5fc17457cacd2)
Powered by SkillShield