Trust Assessment
gallery-scraper 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, 1 high, 0 medium, and 0 low severity. Key findings include Unsafe Automated Clicking of Elements Matching Generic Selectors.
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 October 1, 2026 (commit 439cd3a9). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Unsafe Automated Clicking of Elements Matching Generic Selectors The skill instructs the LLM to automatically click elements matching generic selectors like `[class*='lock']`, `[class*='unlock']`, and `.premium-unlock` on authenticated websites. This is highly dangerous as a malicious or compromised website could present elements matching these selectors that trigger sensitive, state-changing actions (e.g., purchasing premium content, deactivating/locking the account, or initiating transfers) without the user's explicit consent or awareness. Do not automatically click elements on behalf of the user based on generic class or title selectors. Always present the detected elements to the user and require explicit confirmation before performing any click actions on authenticated websites. | LLM | SKILL.md:203 |
Scan History
Embed Code
[](https://skillshield.io/report/366909883e2c19e1)
Powered by SkillShield