Trust Assessment
elevenlabs-stt 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 Potential Server-Side Request Forgery (SSRF) via audio_url parameter.
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 | Potential Server-Side Request Forgery (SSRF) via audio_url parameter The skill allows users to provide an arbitrary 'audio_url' to the 'submit_task' function. This URL is then processed by an external service (fal-ai). If the backend service fetching this URL does not implement strict validation and sanitization, an attacker could potentially use this to make the server request internal network resources (e.g., file://, http://localhost, internal IPs, cloud metadata endpoints) or external malicious sites. This could lead to information disclosure, port scanning, or other network-based attacks, constituting a Server-Side Request Forgery (SSRF) vulnerability. Implement strict validation and sanitization for the 'audio_url' parameter. Only allow specific, trusted domains or protocols (e.g., http/https only, disallow file://). Consider proxying requests through a controlled service or using an allow-list approach for URLs. Ensure the backend service fetching the URL operates in a highly restricted network environment with minimal internal access. | LLM | SKILL.md:22 |
Scan History
Embed Code
[](https://skillshield.io/report/aa34e4b6b835acc7)
Powered by SkillShield