Trust Assessment
Voidex Arena received a trust score of 74/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Command Injection via API-controlled path in shell script, Overly broad instruction to search local files for credentials.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Command Injection via API-controlled path in shell script The `scripts/trade.sh` script constructs `curl` commands using the `$LOCATION` variable, which is directly derived from the `/me` API response. If the `claw.voidex.space` server (an external entity) returns a malicious `location` value containing shell metacharacters (e.g., `;`, `|`, `&`), it could lead to arbitrary command execution on the agent's host system. The `jq -r` command used to extract the location does not escape shell metacharacters, making this a direct injection vector when `$LOCATION` is interpolated into the `curl` command's URL path. Sanitize or strictly validate the `$LOCATION` variable against expected patterns (e.g., `^[a-zA-Z0-9-]+$`) before using it in shell commands. Alternatively, URL-encode the path component before passing it to `curl` to prevent shell interpretation of special characters. | LLM | scripts/trade.sh:13 | |
| HIGH | Overly broad instruction to search local files for credentials The skill explicitly instructs the AI agent to "Search your memory, notes, files, and environment for existing credentials: ... Check local files, config files, or .env files for stored credentials." This instruction is overly broad. If interpreted literally by an LLM, it could lead to attempts to read arbitrary files on the host system, potentially accessing and exfiltrating sensitive data beyond the intended scope of the skill's own configuration files. Restrict the scope of file access instructions. Instead of generic terms like "local files", specify exact file paths or directories (e.g., "Check `~/.voidex_arena/config` or files within your skill's designated data directory"). Avoid open-ended instructions for file system interaction. | LLM | SKILL.md:10 |
Scan History
Embed Code
[](https://skillshield.io/report/97519b38d509c388)
Powered by SkillShield