Trust Assessment
private-connect received a trust score of 10/100, 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: 3 critical, 1 high, 0 medium, and 0 low severity. Key findings include Arbitrary command execution, Remote code execution: curl/wget pipe to shell, Unsafe `curl | bash` installation method.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 55/100, 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/dantelex/private-connect/SKILL.md:68 | |
| 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/dantelex/private-connect/SKILL.md:68 | |
| CRITICAL | Unsafe `curl | bash` installation method The skill's setup instructions recommend installing the `privateconnect` CLI using `curl -fsSL https://privateconnect.co/install.sh | bash`. This method executes an arbitrary script downloaded from the internet without prior review, posing a significant supply chain risk. A compromised `privateconnect.co` domain or `install.sh` script could lead to arbitrary code execution on the user's system with the privileges of the user running the command. Recommend a more secure installation method, such as using official package managers (e.g., apt, yum, brew), signed binaries, or requiring manual download and inspection of the script before execution. Avoid direct piping of remote scripts to `bash`. | LLM | SKILL.md:57 | |
| HIGH | Potential for command injection via external `connect` binary The skill is designed to interact with an external `connect` binary, as indicated by the `gating: {"binary": "connect"}` in the manifest and the various command examples (e.g., `connect_reach`, `connect_share`, `connect_join`). User input for these commands will likely be passed as arguments to the `connect` binary. Without rigorous sanitization of user-provided arguments, a malicious user could inject arbitrary shell commands, leading to command injection. The broad capabilities of the `connect` tool (e.g., 'clone a teammate's entire environment setup') exacerbate the potential impact of such an injection. Ensure all user-provided input passed to the `connect` binary is rigorously sanitized and escaped to prevent shell metacharacter injection. Consider using a safe argument passing mechanism that avoids direct shell interpretation, or explicitly whitelist allowed characters/patterns for arguments. | LLM | SKILL.md:15 |
Scan History
Embed Code
[](https://skillshield.io/report/686a7b29ef7c6549)
Powered by SkillShield