Trust Assessment
flux-image received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 4 findings: 3 critical, 1 high, 0 medium, and 0 low severity. Key findings include Arbitrary command execution, Remote code execution: curl/wget pipe to shell, Direct execution of remote shell script.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 55/100, 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 Findings4
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Remote code download piped to interpreter Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/okaris/flux-image/SKILL.md:9 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/okaris/flux-image/SKILL.md:9 | |
| CRITICAL | Direct execution of remote shell script The skill instructs to download and execute a shell script directly from a URL (`https://cli.inference.sh`) using `curl | sh`. This practice is highly dangerous as it allows arbitrary code execution if the remote script is compromised or malicious. It bypasses local package managers and security checks, posing a severe supply chain risk and command injection vulnerability. Avoid piping `curl` output directly to `sh`. Instead, download the script, inspect it, verify its integrity (e.g., via checksums), and then execute it. Ideally, use a trusted package manager or containerized environment. If `infsh` is a critical dependency, consider packaging it securely or providing a verified installation method. | LLM | SKILL.md:10 | |
| HIGH | Unpinned external package execution via npx The skill suggests using `npx skills add` to install other skills. `npx` executes packages from the npm registry. Without specific version pinning (e.g., `@1.2.3`), this can lead to execution of unverified or potentially malicious code if the package or its dependencies are compromised, or if a typosquatting attack occurs. This introduces a supply chain risk. If `npx` must be used, specify exact versions for packages (e.g., `package@1.2.3`) to prevent unexpected changes. Audit packages and their dependencies for security vulnerabilities. Consider using a secure, sandboxed environment for skill execution. | LLM | SKILL.md:59 |
Scan History
Embed Code
[](https://skillshield.io/report/e0e76a2198594c4c)
Powered by SkillShield