Trust Assessment
fal-ai-media received a trust score of 25/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 2 findings: 1 critical, 1 high, 0 medium, and 0 low severity. Key findings include Unpinned `npx` dependency with auto-confirmation in setup instructions, Arbitrary local file upload capability via `upload` tool.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Static Code Analysis layer scored lowest at 55/100, indicating areas for improvement.
Last analyzed on March 20, 2026 (commit 9a478ad6). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary local file upload capability via `upload` tool The skill exposes an `upload` tool that takes a `file_path` parameter, allowing it to read and upload arbitrary local files from the filesystem. If a malicious prompt can induce the LLM to call this tool with a sensitive `file_path` (e.g., `/etc/passwd`, `~/.ssh/id_rsa`, environment files, or other confidential data), it could lead to severe data exfiltration. This grants the skill excessive permissions to the local filesystem, making it a high-risk vector for prompt injection leading to data leakage. Restrict the `upload` tool's access to specific, user-designated directories (e.g., a temporary upload directory, or a directory explicitly chosen by the user). Implement strict validation on `file_path` inputs to prevent directory traversal attacks or access to sensitive system files. Consider requiring explicit user confirmation for file uploads, especially for non-media files or files outside a designated sandbox. | Static | SKILL.md:48 | |
| HIGH | Unpinned `npx` dependency with auto-confirmation in setup instructions The skill's setup instructions recommend installing `fal-ai-mcp-server` using `npx -y fal-ai-mcp-server`. This command will fetch and execute the latest version of the package from npm without user confirmation. If a malicious version of `fal-ai-mcp-server` is published (e.g., via compromise or typosquatting), users following these instructions could unknowingly execute arbitrary malicious code. The `-y` flag bypasses the crucial user confirmation step, increasing the risk. Specify a precise version for the `fal-ai-mcp-server` package (e.g., `npx -y fal-ai-mcp-server@1.2.3`) to prevent unexpected updates to malicious versions. Additionally, consider removing the `-y` flag to require explicit user confirmation before installation, allowing users to review what they are installing. | Static | SKILL.md:18 |
Scan History
Embed Code
[](https://skillshield.io/report/6dac2f86ebcd56a7)
Powered by SkillShield