Trust Assessment
writing-plans received a trust score of 93/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Skill instructs agent to generate and 'Run' shell commands.
The analysis covered 4 layers: dependency_graph, manifest_analysis, llm_behavioral_safety, static_code_analysis. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 15, 2026 (commit 3e75fabd). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Skill instructs agent to generate and 'Run' shell commands The skill explicitly instructs the agent to generate and then 'Run' shell commands such as `pytest` and `git`. This pattern establishes a direct path for shell execution by the agent. While the commands provided in the skill are templates for benign development operations, the risk lies in the potential for command injection if user-controlled input (e.g., feature name, file paths, test names) were to be unsafely interpolated into these generated commands by the LLM during plan creation. An attacker could craft malicious input that, when substituted into the command template, leads to arbitrary command execution on the host system if the agent's execution environment is not properly sandboxed. 1. Ensure that any user-controlled input used to populate the command templates is rigorously sanitized (e.g., by escaping shell metacharacters) before being included in the generated shell commands. 2. If the agent has a shell execution tool, ensure it operates within a highly sandboxed environment with minimal permissions. 3. Implement explicit checks or warnings within the agent's execution logic to prevent arbitrary command execution from generated output, especially when user input is involved. | Unknown | SKILL.md:79 |
Scan History
Embed Code
[](https://skillshield.io/report/4cfad1407b5fd7b6)
Powered by SkillShield