Security Audit
frankxai/claude-skills-library:free-skills/defuddle
github.com/frankxai/claude-skills-libraryTrust Assessment
frankxai/claude-skills-library:free-skills/defuddle received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Command Injection via Shell Execution of Untrusted URL.
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 October 20, 2026 (commit 93c4aad5). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Command Injection via Shell Execution of Untrusted URL The skill instructs the LLM to execute shell commands using the `defuddle` CLI with a user-provided `<url>` parameter. If the LLM executes this command directly in a shell (e.g., via a bash tool) without strict sanitization, an attacker can inject shell metacharacters (such as `;`, `&&`, `|`, or backticks) into the URL to execute arbitrary commands on the host system. Avoid executing CLI commands directly with raw user input in a shell. If a CLI tool must be used, ensure the LLM or the underlying tool implementation sanitizes the input, or wrap the execution in a safe API/script that does not spawn a shell (e.g., using argument arrays instead of shell strings), or use a dedicated programmatic library instead of a CLI. | LLM | SKILL.md:13 |
Scan History
Embed Code
[](https://skillshield.io/report/30dcfb6c5488daf2)
Powered by SkillShield