Trust Assessment
satori received a trust score of 65/100, 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: 1 critical, 1 high, 0 medium, and 0 low severity. Key findings include Unsanitized user input in shell command execution, Unpinned external CLI dependency.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Unsanitized user input in shell command execution The skill instructs the AI to execute shell commands like `npx -y @satori-sh/cli@latest add "<facts>"` and `npx -y @satori-sh/cli@latest search "<query>"`. The `<facts>` and `<query>` parameters are derived from user input and conversation context. If these inputs are not properly sanitized or shell-escaped before being interpolated into the command string, a malicious user could inject arbitrary shell commands, leading to remote code execution on the host system. For example, an input like `"; rm -rf /"` could be executed. Implement robust input sanitization and shell escaping for all user-derived inputs passed to `npx` commands. Consider using a dedicated library for safe command execution or passing arguments as separate parameters if the CLI supports it, rather than interpolating into a single string. | LLM | SKILL.md:26 | |
| HIGH | Unpinned external CLI dependency The skill uses `npx -y @satori-sh/cli@latest` to execute an external command-line interface. Relying on the `@latest` tag means that any new version of the `@satori-sh/cli` package will be downloaded and executed without explicit version pinning or review. A malicious actor could publish a compromised version of this package, leading to arbitrary code execution, data exfiltration, or other security breaches on the host system when the skill is used. Pin the dependency to a specific, immutable version (e.g., `npx -y @satori-sh/cli@1.2.3`). Regularly review and update the pinned version after verifying its integrity and security. | LLM | SKILL.md:26 |
Scan History
Embed Code
[](https://skillshield.io/report/8634c75b81dc6946)
Powered by SkillShield