Trust Assessment
requesting-code-review received a trust score of 85/100, 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 Potential Command Injection via Shell Execution of Untrusted Placeholders.
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 August 1, 2026 (commit efe1d158). 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 | Potential Command Injection via Shell Execution of Untrusted Placeholders The skill instructs the LLM to run a shell command (`pi -p "prompt from template"`) containing placeholders like `{DESCRIPTION}` and `{WHAT_WAS_IMPLEMENTED}`. If these placeholders are populated with untrusted data (such as commit messages, PR descriptions, or external requirements) containing shell metacharacters, it can lead to arbitrary command execution when the LLM executes the command in a shell. Avoid executing shell commands with untrusted placeholder values. Instead of running `pi -p` via shell, use a dedicated API, dispatch tool, or instruct the user to run the command, or ensure strict escaping/sanitization of the placeholder values before shell execution. | LLM | SKILL.md:35 |
Scan History
Embed Code
[](https://skillshield.io/report/232de167fba07206)
Powered by SkillShield