Trust Assessment
vapi received a trust score of 21/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 4 findings: 2 critical, 1 high, 1 medium, and 0 low severity. Key findings include Arbitrary command execution, Missing required field: name, Remote code execution: curl/wget pipe to shell.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Static Code Analysis layer scored lowest at 63/100, indicating areas for improvement.
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 Findings4
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Remote code download piped to interpreter Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/colygon/vapi/SKILL.md:85 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/colygon/vapi/SKILL.md:85 | |
| HIGH | API Key Exfiltration via Malicious VAPI_BASE_URL The `bin/vapi-api.mjs` script allows the Vapi API base URL to be overridden via the `VAPI_BASE_URL` environment variable. If an AI agent is prompted to execute this script and can be manipulated to set `VAPI_BASE_URL` to an attacker-controlled endpoint, the `VAPI_API_KEY` (sent in the Authorization header) will be exfiltrated to the malicious server. This constitutes a data exfiltration vulnerability through prompt injection targeting environment variables. Implement strict validation or whitelisting for `VAPI_BASE_URL` if it's intended to be configurable by the agent. Alternatively, ensure the agent's execution environment prevents untrusted input from setting critical environment variables for skill execution. If the skill is only meant to use the default Vapi API, remove the `process.env.VAPI_BASE_URL` override. | LLM | bin/vapi-api.mjs:6 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/colygon/vapi/SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/a9bdc1ded478df94)
Powered by SkillShield