Trust Assessment
run-nx-generator received a trust score of 94/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 2 findings: 0 critical, 0 high, 0 medium, and 2 low severity. Key findings include Broad Bash permission declared, Broad filesystem access permissions declared.
The analysis covered 4 layers: manifest_analysis, llm_behavioral_safety, static_code_analysis, dependency_graph. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 11, 2026 (commit f4b5c7d6). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| LOW | Broad Bash permission declared The skill declares `Bash` as an allowed tool in its manifest. While necessary for its core function of running `nx generate` commands, `Bash` grants the ability to execute arbitrary shell commands. This capability, if misused by the LLM (e.g., by passing unsanitized user input as arguments to `nx generate`), could lead to command injection vulnerabilities. The skill itself, being a rubric, does not explicitly instruct execution, but the declared permission enables this potential risk. Implement strict input validation and sanitization for any arguments passed to `nx generate` or other `Bash` commands derived from untrusted user input. Consider using more specific tools if possible, or sandboxing `Bash` execution to limit its scope. | Unknown | SKILL.md:1 | |
| LOW | Broad filesystem access permissions declared The skill declares `Read`, `Glob`, and `Grep` as allowed tools in its manifest. These permissions grant broad access to the filesystem, allowing the agent to read, list, and search arbitrary files. While potentially necessary for understanding the monorepo structure or generator configurations, these capabilities could be misused by the LLM to exfiltrate sensitive data or gain unauthorized information about the system if not carefully controlled. The skill itself, being a rubric, does not explicitly instruct execution, but the declared permissions enable this potential risk. Restrict filesystem access to the absolute minimum necessary directories and file types. Implement strict validation on any file paths or patterns derived from untrusted user input before using `Read`, `Glob`, or `Grep`. | Unknown | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/18fe0aea0a31d84d)
Powered by SkillShield