Trust Assessment
fd-find received a trust score of 96/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Skill documents command execution feature (`-x`).
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 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Skill documents command execution feature (`-x`) The skill's documentation (`SKILL.md`) prominently features examples of `fd`'s `-x` flag and piping to `xargs`. These mechanisms allow arbitrary command execution on files found by `fd`. If the host LLM constructs `fd -x` or `xargs` commands based on untrusted user input without proper sanitization, it could lead to command injection and arbitrary code execution on the system where the LLM agent operates. While the skill itself does not execute these commands, it provides the LLM with the knowledge and examples to do so, thereby exposing a potential command injection vector. Add explicit warnings in the skill documentation about the dangers of using `-x` or `xargs` with untrusted input. Advise the LLM to sanitize user-provided commands or arguments before incorporating them into `fd -x` or `xargs` constructs. Consider providing safer alternatives or helper functions that abstract away direct shell execution, or restrict the types of commands that can be executed via `-x`. | LLM | SKILL.md:70 |
Scan History
Embed Code
[](https://skillshield.io/report/c8bb4195df30d729)
Powered by SkillShield