Security Audit
canva-automation
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
canva-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 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Potential data exfiltration via URL-based content 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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Potential data exfiltration via URL-based content upload The skill documentation describes tools that allow the LLM to upload content from a specified URL. Specifically, `CANVA_CREATE_ASSET_UPLOAD_JOB` takes a `url` parameter for asset uploads, and `CANVA_INITIATE_CANVA_DESIGN_AUTOFILL_JOB` can accept 'image URL' as data values for placeholders. If the LLM is prompted by a malicious user, it could be instructed to provide a URL pointing to sensitive internal data (e.g., an internal document server, or a local file exposed via a web server accessible to the LLM's execution environment). This would lead to the exfiltration of that data to Canva. While this is intended functionality of the tools, it presents a risk if the LLM is not properly secured against malicious prompts. Implement strict URL validation and allow-listing for content uploads if possible. Ensure the LLM's execution environment does not have network access to sensitive internal resources that should not be exfiltrated. Educate the LLM on not uploading sensitive data from arbitrary URLs provided by untrusted user input. | LLM | SKILL.md:72 |
Scan History
Embed Code
[](https://skillshield.io/report/b46fe001e88a5fe7)
Powered by SkillShield