Security Audit

cal-com-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

cal-com-automation received a trust score of 82/100, 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, 1 medium, and 0 low severity. Key findings include Potential Data Exfiltration via Malicious Webhook Configuration, Unversioned External MCP Dependency Poses Supply Chain Risk.

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

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

78%

Behavioral Risk Signals

Network Access

2 findings

Shell Execution

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Potential Data Exfiltration via Malicious Webhook Configuration The skill exposes tools that allow an agent to configure Cal.com webhooks, specifically `CAL_UPDATE_WEBHOOK_BY_ID`. The `subscriberUrl` parameter can be set to an arbitrary URL. If an attacker can prompt the agent to set a malicious `subscriberUrl`, sensitive Cal.com event data (e.g., booking details, attendee information) could be exfiltrated to an attacker-controlled server when events trigger the webhook. Implement strict validation or allowlisting for webhook `subscriberUrl`s. Require explicit user confirmation or a human-in-the-loop for any changes to webhook configurations, especially for `subscriberUrl`. Ensure the LLM agent is constrained from setting arbitrary URLs.	LLM	SKILL.md:100
MEDIUM	Unversioned External MCP Dependency Poses Supply Chain Risk The skill explicitly relies on an external Rube MCP server at `https://rube.app/mcp` without specifying a version or providing integrity checks for the tools it serves. A compromise of the `rube.app` domain or the MCP server could lead to the skill executing malicious or altered tools, introducing a supply chain vulnerability. If possible, implement version pinning for the Rube MCP or require cryptographic signatures/hashes for the tools served by the MCP to ensure their integrity. Evaluate the trust model and security posture of `rube.app`.	LLM	SKILL.md:30

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/efe4af26db4c9ac9.svg)](https://skillshield.io/report/efe4af26db4c9ac9)