Trust Assessment
ad-ready received a trust score of 82/100, 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 Arbitrary file write via --output argument, Server-Side Request Forgery (SSRF) vulnerability via --product-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 February 13, 2026 (commit 13146e6a). 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 | Arbitrary file write via --output argument The script allows the user to specify an arbitrary file path for the output image using the `--output` argument. The `download_to_file` function then writes the downloaded image content directly to this path (`Path(args.output)`) without any sanitization or restriction to a safe directory. An attacker could exploit this to overwrite critical system files (e.g., `/etc/passwd`, `~/.bashrc`) or place malicious files in sensitive locations. Restrict the `--output` path to a designated safe directory (e.g., a subdirectory within the skill's working directory or a user-specific output directory). Implement path sanitization to prevent directory traversal (e.g., `../`) and ensure the path is within the allowed scope. | LLM | scripts/generate.py:400 | |
| MEDIUM | Server-Side Request Forgery (SSRF) vulnerability via --product-url The script fetches content from the `--product-url` using `httpx.get` without validating the URL's scheme or host. An attacker could provide an internal IP address or a `file://` URL (though `httpx` might not support `file://` directly) to make the agent request internal network resources. This could lead to information disclosure, port scanning, or denial-of-service against internal services if the agent is running in a privileged network environment. Implement robust URL validation to ensure `product_url` points to an external, public HTTP/HTTPS resource. This should involve checking the URL scheme, resolving the hostname to ensure it's not a private IP address, and potentially using a whitelist of allowed domains or a blacklist of private IP ranges. | LLM | scripts/generate.py:200 |
Scan History
Embed Code
[](https://skillshield.io/report/8ba9f974c2104b22)
Powered by SkillShield