Trust Assessment
calendly 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 Command Injection via Unsanitized Placeholders.
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 12, 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 Command Injection via Unsanitized Placeholders The `curl` commands provided as examples contain placeholders such as `USERID`, `{uuid}`, and `{event_uuid}`. If an LLM is used to construct and execute these commands by substituting these placeholders with untrusted user input without proper sanitization or escaping, it could lead to arbitrary command injection. A malicious user could inject shell commands (e.g., `$(malicious_command)`) into these placeholders, leading to unauthorized execution on the host system. Implement robust input validation and sanitization for all user-provided inputs before substituting them into shell commands. Ensure that any dynamic parts of the command are properly escaped to prevent shell metacharacter interpretation. Consider using a dedicated API client library instead of raw `curl` commands for safer parameter handling. | LLM | SKILL.md:19 |
Scan History
Embed Code
[](https://skillshield.io/report/08938d3c3d7f3a92)
Powered by SkillShield