Trust Assessment
writing-plans received a trust score of 73/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Command Injection via Unsanitized Plan Generation.
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 20, 2026 (commit e36d6fd3). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Command Injection via Unsanitized Plan Generation The `writing-plans` skill generates markdown plans containing shell commands (e.g., `git`, `pytest`) and file paths, which are explicitly intended for execution by the `executing-plans` skill. If untrusted user input (such as feature names, component names, or file paths) is directly embedded into these commands or paths within the generated plan without proper sanitization, it creates a critical command injection vulnerability. A malicious user could craft input that, when included in the plan and subsequently executed by `executing-plans`, leads to arbitrary command execution on the host system. Instruct the LLM to strictly sanitize all user-provided input before embedding it into any part of the generated plan that could be interpreted as a shell command argument, file path, or part of a command string. This includes, but is not limited to, feature names used in filenames (e.g., `docs/plans/YYYY-MM-DD-<feature-name>.md`), component names, and any dynamic parts of `git commit` messages or `pytest` commands. Implement robust input validation and escaping mechanisms to prevent shell metacharacters or path traversal sequences from being processed as commands. | LLM | SKILL.md:68 |
Scan History
Embed Code
[](https://skillshield.io/report/5a2f13d4576dcc83)
Powered by SkillShield