Trust Assessment
opnsense-admin received a trust score of 73/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 3 findings: 0 critical, 2 high, 0 medium, and 1 low severity. Key findings include Potential Command Injection via Sourced Credentials File, High Privilege Access Required for Skill Operation.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 68/100, indicating areas for improvement.
Last analyzed on February 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via Sourced Credentials File The scripts `scripts/backup-config.sh` and `scripts/opnsense-api.sh` use `source ~/.opnsense/credentials` to load API keys and other configuration. If this credentials file is compromised or contains malicious shell commands, the `source` command will execute them directly, leading to arbitrary command execution on the host system. While the `SKILL.md` recommends securing this file with `chmod 600`, the reliance on sourcing an external file for execution context introduces a significant risk if the file's integrity is not guaranteed or if it's inadvertently created with untrusted content. 1. Ensure the `~/.opnsense/credentials` file is strictly controlled, created by a trusted source, and secured with `chmod 600` as recommended. 2. Consider alternative, more secure methods for credential management that do not involve sourcing arbitrary shell scripts, such as using a dedicated credential store or passing credentials directly as environment variables without sourcing. 3. Implement integrity checks for the credentials file before sourcing it. | LLM | scripts/backup-config.sh:14 | |
| HIGH | Potential Command Injection via Sourced Credentials File The scripts `scripts/backup-config.sh` and `scripts/opnsense-api.sh` use `source ~/.opnsense/credentials` to load API keys and other configuration. If this credentials file is compromised or contains malicious shell commands, the `source` command will execute them directly, leading to arbitrary command execution on the host system. While the `SKILL.md` recommends securing this file with `chmod 600`, the reliance on sourcing an external file for execution context introduces a significant risk if the file's integrity is not guaranteed or if it's inadvertently created with untrusted content. 1. Ensure the `~/.opnsense/credentials` file is strictly controlled, created by a trusted source, and secured with `chmod 600` as recommended. 2. Consider alternative, more secure methods for credential management that do not involve sourcing arbitrary shell scripts, such as using a dedicated credential store or passing credentials directly as environment variables without sourcing. 3. Implement integrity checks for the credentials file before sourcing it. | LLM | scripts/opnsense-api.sh:14 | |
| LOW | High Privilege Access Required for Skill Operation The skill is designed for OPNsense firewall administration and explicitly requires high-privilege access, including OPNsense API keys with broad permissions and SSH access as the `root` user. While this level of access is necessary for the skill's intended functionality and is clearly documented in the `SKILL.md` disclaimer, it inherently increases the potential impact and blast radius in the event of a compromise of the skill or the environment it operates within. 1. Adhere strictly to the security best practices outlined in the `SKILL.md`, particularly restricting API permissions to the absolute minimum required. 2. Ensure the environment where this skill is executed is highly secured, isolated, and regularly monitored. 3. Implement robust access controls and regularly audit access logs on the OPNsense firewall for any unusual activity. | LLM | SKILL.md:5 |
Scan History
Embed Code
[](https://skillshield.io/report/f3a45306b3aff1e1)
Powered by SkillShield