Trust Assessment
coding-agent 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 3 findings: 1 critical, 2 high, 0 medium, and 0 low severity. Key findings include Obfuscated remote code execution during MacOS setup, Unpinned global package installations.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 40/100, indicating areas for improvement.
Last analyzed on February 12, 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 | |
|---|---|---|---|---|
| CRITICAL | Obfuscated remote code execution during MacOS setup The MacOS setup instructions include a base64-encoded command that, when decoded, downloads and executes a shell script from an unverified IP address (http://91.92.242.30/tjjve9itarrd3txw) without any integrity checks. This allows for arbitrary code execution from an untrusted source, posing a severe supply chain risk and potential for system compromise. The use of base64 encoding also constitutes hidden instructions. Remove the base64-encoded command. Provide a clear, verifiable installation method, preferably using a package manager or a script from a trusted, version-controlled source with integrity checks (e.g., checksums, signed packages). Avoid direct execution of remote scripts without verification. | LLM | SKILL.md:14 | |
| HIGH | Unpinned global package installations The skill instructs users to install global npm and pnpm packages (`@mariozechner/pi-coding-agent`) without specifying exact versions. This introduces a supply chain risk, as a malicious or vulnerable update to the package could be automatically installed, leading to potential compromise or unexpected behavior. Always specify exact versions for package installations (e.g., `npm install -g @mariozechner/pi-coding-agent@1.2.3`). Consider using a lock file or a more robust dependency management system for reproducible and secure installations. | LLM | SKILL.md:90 | |
| HIGH | Unpinned global package installations The skill instructs users to install global npm and pnpm packages (`@mariozechner/pi-coding-agent`) without specifying exact versions. This introduces a supply chain risk, as a malicious or vulnerable update to the package could be automatically installed, leading to potential compromise or unexpected behavior. Always specify exact versions for package installations (e.g., `npm install -g @mariozechner/pi-coding-agent@1.2.3`). Consider using a lock file or a more robust dependency management system for reproducible and secure installations. | LLM | SKILL.md:120 |
Scan History
Embed Code
[](https://skillshield.io/report/0afe62c6c43cecec)
Powered by SkillShield