Security Audit
sandwichfarm/hyprfx:.skills/install
github.com/sandwichfarm/hyprfxTrust Assessment
sandwichfarm/hyprfx:.skills/install received a trust score of 81/100, 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 Sudo Commands, Unpinned Git Repository for Dependency Installation.
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 23, 2026 (commit b6089954). 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 Sudo Commands The skill provides explicit `sudo` commands for installing system packages (e.g., `sudo pacman -S ...`, `sudo dnf install ...`). Although there's an instruction 'do NOT run sudo yourself' for the agent, a malicious user could easily prompt the agent to copy and execute these commands, leading to arbitrary command execution with root privileges on the host system. The agent should not be capable of directly executing commands presented in the skill without explicit, sandboxed user confirmation. Agents should be strictly sandboxed and require explicit user confirmation for any command execution, especially those involving `sudo`. The skill itself could be improved by rephrasing these as 'User should run: `sudo pacman -S ...`' to emphasize user action, or by providing a tool that generates the command for the user to copy, rather than presenting it as an agent-executable command. | LLM | SKILL.md:35 | |
| MEDIUM | Unpinned Git Repository for Dependency Installation The skill instructs the use of `hyprpm add https://github.com/sandwichfarm/hyprfx` and `git pull` for installation and updates. These commands fetch code directly from the `main` branch of a Git repository without specifying a commit hash or tag. This introduces a supply chain risk, as a compromise of the upstream repository could lead to the installation of malicious code on the user's system during initial setup or subsequent updates. Pin dependencies to specific commit hashes or tags (e.g., `hyprpm add https://github.com/sandwichfarm/hyprfx@v1.0.0` or `git checkout <commit_hash>`). Implement integrity checks (e.g., checksum verification) for fetched code. | LLM | SKILL.md:20 |
Scan History
Embed Code
[](https://skillshield.io/report/636bfc39cb3b5b74)
Powered by SkillShield