Trust Assessment
open-claw-mind received a trust score of 83/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 3 findings: 0 critical, 0 high, 3 medium, and 0 low severity. Key findings include Missing required field: name, Credential Exposure in `curl` Examples, Potential Command Injection via `claude_desktop_config.json` `args`.
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 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| 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/teylersf/open-claw-mind/SKILL.md:1 | |
| MEDIUM | Credential Exposure in `curl` Examples The provided `curl` examples instruct users to include sensitive credentials (API keys, passwords) directly in command-line arguments or POST data. When executed, these commands can leave these credentials in shell history files (e.g., `.bash_history`, `.zsh_history`), making them vulnerable to discovery by other users or processes on the same system. While this is a user-side risk, the skill documentation promotes this insecure practice. Advise users to store API keys and passwords in environment variables or secure configuration files, and reference them in `curl` commands (e.g., `curl -H "X-API-Key: $OPENCLAW_API_KEY" ...`). For passwords, recommend using a password manager or interactive input methods where possible, or at least caution against direct command-line inclusion. | LLM | SKILL.md:20 | |
| MEDIUM | Potential Command Injection via `claude_desktop_config.json` `args` The `claude_desktop_config.json` example shows a `command` field set to `"curl"` and an `args` array containing `"X-API-Key: YOUR_API_KEY"`. If the `YOUR_API_KEY` value or any other part of the `args` array were to be dynamically generated or influenced by untrusted input, it could lead to command injection. An attacker could craft a malicious API key or other argument to execute arbitrary shell commands on the system where the Claude Desktop agent is running. Although the example shows a placeholder, the structure itself presents a vulnerability if not handled with strict input validation by the consuming agent runtime. The agent runtime consuming this configuration should implement robust input validation and sanitization for all elements within the `args` array to prevent shell metacharacters or other malicious input from being executed. Consider using a more secure method for passing sensitive data than direct command-line arguments, such as environment variables or secure credential stores, which are then referenced by the `curl` command. | LLM | SKILL.md:39 |
Scan History
Embed Code
[](https://skillshield.io/report/f4dd652825541180)
Powered by SkillShield