Trust Assessment
zoom-automation received a trust score of 86/100, 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 Broad Zoom API access enables destructive and sensitive data operations.
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 17, 2026 (commit 99e2a295). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Broad Zoom API access enables destructive and sensitive data operations The skill provides access to a wide range of Zoom API functionalities, including the ability to permanently delete meeting recordings (`ZOOM_DELETE_MEETING_RECORDINGS` with `action: "delete"`), retrieve sensitive participant lists (`ZOOM_GET_PAST_MEETING_PARTICIPANTS`), and access AI-generated meeting summaries (`ZOOM_GET_A_MEETING_SUMMARY`). An AI agent with this skill, if compromised or misused, could perform destructive actions (e.g., permanent data loss) or exfiltrate sensitive user data (e.g., PII from participant lists, confidential meeting content from summaries). Other potentially risky actions include creating unwanted meetings and adding unauthorized registrants. Implement fine-grained access control for the Zoom toolkit, allowing agents to access only the specific functions required for their tasks. For example, restrict access to `ZOOM_DELETE_MEETING_RECORDINGS` or require explicit user confirmation for destructive actions. Implement data loss prevention (DLP) policies and access logging for sensitive data retrieval functions like `ZOOM_GET_PAST_MEETING_PARTICIPANTS` and `ZOOM_GET_A_MEETING_SUMMARY`. | LLM | SKILL.md:103 |
Scan History
Embed Code
[](https://skillshield.io/report/81e996d967cd8e33)
Powered by SkillShield