Trust Assessment
migrate-to-rslint 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 2 findings: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via Lint/Fix Commands, Broad Filesystem and Execution Permissions Required.
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 June 1, 2026 (commit 76880945). 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 | Potential Command Injection via Lint/Fix Commands The skill explicitly instructs the agent to 'Run the migrated lint command' and 'run the migrated fix command'. This indicates that the agent will generate and execute shell commands. If the construction of these commands incorporates untrusted input (e.g., from user-provided linter names, project configuration, or existing scripts), it could lead to command injection, allowing arbitrary code execution within the agent's environment or the user's project. Ensure all commands generated and executed by the agent are strictly sanitized and validated. Avoid directly embedding untrusted strings into shell commands. Consider using a safe command execution mechanism that separates command arguments from the command itself, or whitelist allowed commands and arguments. | LLM | SKILL.md:40 | |
| INFO | Broad Filesystem and Execution Permissions Required The skill's functionality, which involves detecting source linters, applying migration guides, validating behavior, and cleaning up (e.g., 'remove obsolete linter dependencies/config'), inherently requires broad read, write, and execution permissions on the project's filesystem. While necessary for the skill's purpose, this broad scope means that a compromised agent executing this skill could have significant impact on the user's project. Implement strict sandboxing and least-privilege principles for the agent's execution environment. Ensure that the agent's access is limited to only what is absolutely necessary for the skill to function, and that any file modifications or command executions are confirmed with the user where appropriate. | LLM | SKILL.md:10 |
Scan History
Embed Code
[](https://skillshield.io/report/d4937f3800c63800)
Powered by SkillShield