Security Audit

nicobailon/visual-explainer:plugins/visual-explainer

github.com/nicobailon/visual-explainer

AI SkillCommit 61f06e818e8f

TRUSTED

Scanned 17 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

nicobailon/visual-explainer:plugins/visual-explainer 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, 1 high, 0 medium, and 0 low severity. Key findings include Public Exposure of Sensitive Data via Vercel Deployment, Unpinned Dependency Recommendation.

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 March 21, 2026 (commit 61f06e81). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

85%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Public Exposure of Sensitive Data via Vercel Deployment The `share.sh` script is designed to deploy user-generated HTML files to Vercel, making them publicly accessible via a live URL. The `SKILL.md` explicitly encourages generating HTML pages for content such as 'diff review', 'plan review', 'project recap', and 'fact-check'. These types of documents are highly likely to contain sensitive, proprietary, or confidential information (e.g., code changes, internal project plans, security assessments). Deploying such content to a public platform like Vercel without explicit user confirmation of the sensitivity of the content constitutes a significant data exfiltration risk. Before deploying, the skill should explicitly prompt the user to confirm that the content of the HTML file is not sensitive and is suitable for public sharing. Alternatively, provide an option to deploy to a private or password-protected environment if Vercel supports it, or clearly warn the user about the public nature of the deployment and advise against sharing sensitive data. The `SKILL.md` should also include a prominent warning about the public nature of shared content.	Static	scripts/share.sh:1
INFO	Unpinned Dependency Recommendation The `share.sh` script suggests installing the `vercel-deploy` skill using `pi install npm:vercel-deploy` if it's not found. This recommendation does not specify a version or commit hash for the `vercel-deploy` skill, which introduces a supply chain risk. If a malicious version of `vercel-deploy` were published to the npm registry, users following this recommendation could inadvertently install compromised software. When recommending skill installations, always specify a pinned version (e.g., `pi install npm:vercel-deploy@1.2.3`) or a specific commit hash to ensure reproducibility and mitigate the risk of installing a compromised package. The `SKILL.md` or installation instructions should also reflect this best practice.	Static	scripts/share.sh:30

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/51e40fab5511fa84.svg)](https://skillshield.io/report/51e40fab5511fa84)