Trust Assessment
codemod-gen received a trust score of 82/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Potential Command Injection via `npx` argument, Unpinned `npx` dependency for `ai-codemod`.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Unpinned `npx` dependency for `ai-codemod` The skill relies on `npx ai-codemod` without specifying a version. This means `npx` will always fetch the latest available version from the npm registry. This introduces a significant supply chain risk, as a malicious update to the `ai-codemod` package or a typosquatting attack could compromise the AI agent's execution environment. Pin the version of the `ai-codemod` package (e.g., `npx ai-codemod@1.2.3`) to ensure deterministic and secure execution. Regularly review and update the pinned version after verifying its integrity. | LLM | SKILL.md:15 | |
| MEDIUM | Potential Command Injection via `npx` argument The skill instructs the AI agent to execute `npx ai-codemod` with a natural language description as an argument. If the AI agent directly interpolates user-provided input into this argument without proper sanitization or escaping, it could lead to command injection, allowing an attacker to execute arbitrary commands on the host system. The AI agent should implement robust input sanitization and escaping for any user-provided text before constructing and executing the `npx ai-codemod` command. Consider using a dedicated library for command argument escaping. | LLM | SKILL.md:15 |
Scan History
Embed Code
[](https://skillshield.io/report/660091a301a3fa39)
Powered by SkillShield