Trust Assessment
reminders received a trust score of 73/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via osascript arguments.
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 | |
|---|---|---|---|---|
| CRITICAL | Potential Command Injection via osascript arguments The `references/reminders.sh` script dynamically constructs JavaScript for Automation (JXA) commands using `osascript` and embeds user-provided arguments directly into the JXA script string. Without proper escaping of these arguments, a malicious user input could break out of the JXA string context and execute arbitrary JXA code or shell commands via `do shell script`. This could lead to data exfiltration, system modification, or other unauthorized actions. Ensure all user-provided arguments passed to `osascript` are properly escaped for JXA context. This typically involves escaping single quotes, backslashes, and other special characters. A safer approach might be to pass arguments via environment variables or temporary files if direct string interpolation cannot be made robustly secure. | LLM | references/reminders.sh:150 |
Scan History
Embed Code
[](https://skillshield.io/report/2716937ac7dea9d9)
Powered by SkillShield