Trust Assessment
code-standards-analyzer received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Excessive 'Bash' permission declared.
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 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Excessive 'Bash' permission declared The skill declares the 'Bash' permission, which allows arbitrary shell command execution. While the skill describes a code analysis function that might require invoking external tools (e.g., linters, formatters, static analyzers) for various languages, the 'Bash' permission grants broad system access. If the skill's underlying implementation constructs shell commands using untrusted input (e.g., file paths, user-provided patterns, code snippets), it could lead to severe command injection vulnerabilities. The `SKILL.md` itself does not demonstrate such an exploit, but the declaration of this powerful permission for a skill processing arbitrary code is a significant security risk. Review the necessity of the 'Bash' permission. If external tools must be invoked, consider using more constrained execution environments or specific tool integrations rather than a general 'Bash' permission. Ensure all inputs to shell commands are rigorously sanitized and validated to prevent command injection. If possible, use dedicated APIs or libraries for code analysis instead of shelling out to system commands. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/655cdce4a182bedc)
Powered by SkillShield