Trust Assessment
mac-node-snapshot received a trust score of 68/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 3 findings: 0 critical, 2 high, 1 medium, and 0 low severity. Key findings include Potential Command Injection via `openclaw nodes screen record --node` argument, Skill requires highly sensitive Screen Recording permissions, Reliance on unpinned system binaries (`openclaw`, `ffmpeg`).
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 63/100, indicating areas for improvement.
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 | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via `openclaw nodes screen record --node` argument The `openclaw nodes screen record` command in the skill's `Quick start` section uses a placeholder `<node>` for its `--node` argument. If this placeholder is populated directly from untrusted user input without proper sanitization or validation, an attacker could inject arbitrary shell commands. For example, by providing a value like `my_node" --evil-arg "value` or `my_node"; rm -rf /; #`, an attacker could execute malicious commands on the host system. Ensure that the `<node>` parameter is strictly validated and sanitized to prevent shell metacharacters or command injection. Ideally, use a dedicated API or library function for node selection that does not involve direct shell string interpolation, or escape the input thoroughly before execution. | LLM | SKILL.md:13 | |
| HIGH | Skill requires highly sensitive Screen Recording permissions The core functionality of this skill involves recording the user's screen using `openclaw nodes screen record`. This operation requires granting 'Screen Recording' permissions in macOS System Settings, which provides the skill with access to all visual content displayed on the user's screen. While necessary for the skill's intended purpose, this is a highly sensitive permission that could be misused if the skill were compromised or if the user is unaware of the full scope of data access. Clearly communicate the necessity and implications of granting screen recording permissions to the user before skill activation. Implement robust security measures to protect the captured screen data and ensure it is only used for the intended purpose. | LLM | SKILL.md:5 | |
| MEDIUM | Reliance on unpinned system binaries (`openclaw`, `ffmpeg`) The skill executes external system binaries `openclaw` and `ffmpeg` without specifying or verifying their versions. This introduces a supply chain risk, as the skill's behavior is dependent on the versions of these tools installed on the host system. If a malicious or vulnerable version of `openclaw` or `ffmpeg` were present, the skill could inadvertently execute compromised code or exhibit unintended behavior. Where possible, specify exact versions for external dependencies and include mechanisms to verify their integrity (e.g., checksums). For system-level binaries, provide clear installation instructions with recommended versions, and consider adding checks within the skill to verify the installed versions before execution. | LLM | SKILL.md:13 |
Scan History
Embed Code
[](https://skillshield.io/report/ec4dea6ecb8a0553)
Powered by SkillShield