Security Audit
webflow-automation
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
webflow-automation 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 2 findings: 0 critical, 0 high, 2 medium, and 0 low severity. Key findings include Unpinned dependency in manifest, Potential data exfiltration via arbitrary file upload.
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 20, 2026 (commit e36d6fd3). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Unpinned dependency in manifest The skill manifest specifies a dependency on the 'rube' MCP without a version constraint. This allows any version of 'rube' to be used, which could introduce vulnerabilities if a future version contains malicious code or breaking changes, or if an incompatible version is loaded. Pin the 'rube' dependency to a specific, known-good version or a version range (e.g., `"rube": ["~1.0.0"]`) to ensure consistent and secure behavior. | LLM | SKILL.md:1 | |
| MEDIUM | Potential data exfiltration via arbitrary file upload The `WEBFLOW_UPLOAD_ASSET` tool allows uploading arbitrary base64-encoded file content to a Webflow site. If the host LLM has access to local file systems and can be prompted by a malicious user to read sensitive files (e.g., credentials, configuration files), it could then use this tool to exfiltrate that data by uploading it to a controlled Webflow site. While the skill itself does not instruct file reading, the presence of a general-purpose file upload tool creates a significant risk surface. Implement strict sandboxing for the LLM to prevent local file system access. Ensure the LLM is trained or guarded against providing sensitive local file content to upload tools. Consider adding user confirmation steps for any asset uploads, especially if the content is not explicitly provided by the user. | LLM | SKILL.md:199 |
Scan History
Embed Code
[](https://skillshield.io/report/f27aaddc60b46390)
Powered by SkillShield