Trust Assessment
best-practices received a trust score of 94/100, 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 Orchestrates agent with broad filesystem read access.
The analysis covered 4 layers: manifest_analysis, llm_behavioral_safety, static_code_analysis, dependency_graph. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 11, 2026 (commit 6195a031). 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 | Orchestrates agent with broad filesystem read access The `best-practices` skill orchestrates the use of the `codebase-context-builder` agent, which is described as having the mission to 'Explore THIS codebase'. This implies read access to all files within the repository. While this level of access might be intended for comprehensive code analysis, it represents an overly broad filesystem scope for an agent. This increases the risk of accidental data exposure or exfiltration if the agent's output is not carefully controlled, or if the agent itself is compromised. The `best-practices` skill itself does not directly perform this action but instructs another agent within the same package to do so. 1. **Scope down access**: If possible, restrict the `codebase-context-builder` agent's filesystem access to only necessary directories or file types required for its specific tasks. 2. **Justify broad access**: Clearly document why full codebase read access is required for the `codebase-context-builder` agent and what safeguards are in place to prevent misuse or data leakage. 3. **Review `codebase-context-builder` implementation**: Ensure the actual implementation of `agents/codebase-context-builder.md` strictly adheres to its stated mission and does not have unintended side effects or vulnerabilities. | Unknown | SKILL.md:44 |
Scan History
Embed Code
[](https://skillshield.io/report/e8084e2b905bac95)
Powered by SkillShield