Security Audit
azure-communication-callautomation-java
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
azure-communication-callautomation-java 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, 0 high, 1 medium, and 0 low severity. Key findings include Potential Server-Side Request Forgery (SSRF) via external URL.
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 e36d6fd3). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Potential Server-Side Request Forgery (SSRF) via external URL The `callRecording.downloadTo` method is shown consuming `recordingUrl`, which is explicitly stated to originate from a `RecordingFileStatusUpdated event`. If an attacker can manipulate or spoof this external event, they could provide an arbitrary URL for `recordingUrl`. This could lead to Server-Side Request Forgery (SSRF), compelling the application to make requests to internal network resources or attacker-controlled external servers, potentially leading to data exfiltration, port scanning, or other malicious activities. Implement robust validation and sanitization for `recordingUrl` received from external events. Ensure the URL points to an expected and trusted domain/resource. Consider using a whitelist of allowed domains or strictly validating the URL structure and scheme (e.g., only `https`). | LLM | SKILL.md:108 |
Scan History
Embed Code
[](https://skillshield.io/report/052537af661027b9)
Powered by SkillShield