Trust Assessment
cal-com-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 Webhook management allows data exfiltration to arbitrary URLs.
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 13, 2026 (commit 13146e6a). 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 | Webhook management allows data exfiltration to arbitrary URLs The skill provides tools to manage Cal.com webhooks, specifically `CAL_UPDATE_WEBHOOK_BY_ID`. This tool allows setting the `subscriberUrl` parameter to an arbitrary endpoint. If an attacker can manipulate this parameter through a malicious prompt, they could configure webhooks to send sensitive Cal.com event data (e.g., booking details, attendee names, emails, event types) to an attacker-controlled server, leading to data exfiltration. Implement strict validation and allowlisting for `subscriberUrl` parameters. If possible, restrict the ability to set arbitrary webhook URLs, or require explicit user confirmation for new/changed webhook URLs. Ensure the LLM is explicitly instructed to only use trusted, pre-approved URLs for webhooks. | LLM | SKILL.md:90 |
Scan History
Embed Code
[](https://skillshield.io/report/4348c704860e0a49)
Powered by SkillShield