Security Audit
Webex Automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
Webex Automation 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 Webhook targetUrl allows arbitrary data exfiltration.
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 20, 2026 (commit 27904475). 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 targetUrl allows arbitrary data exfiltration The `WEBEX_WEBHOOKS_CREATE_WEBHOOK` tool explicitly allows the agent to create webhooks with a user-provided `targetUrl`. This means an attacker could instruct the agent to set up a webhook that forwards sensitive Webex data (such as messages, room activity, or membership changes, depending on the `resource` and `event` parameters) to an arbitrary external server controlled by the attacker. This presents a direct and high-impact data exfiltration vector. Implement strict validation or allowlisting for `targetUrl` values. If arbitrary URLs must be supported, require explicit user confirmation for webhook creation to external domains. Consider proxying webhooks through a controlled service that can filter or redact sensitive information before forwarding. | LLM | SKILL.md:61 |
Scan History
Embed Code
[](https://skillshield.io/report/ad79d3537a60605d)
Powered by SkillShield