Security Audit
lead-research-assistant
github.com/davila7/claude-code-templatesTrust Assessment
lead-research-assistant received a trust score of 76/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 3 findings: 0 critical, 1 high, 1 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, Excessive Permissions: Broad codebase analysis instruction.
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 12, 2026 (commit 458b1186). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Excessive Permissions: Broad codebase analysis instruction The skill instructs the LLM to 'analyze the codebase to understand the product' if run from a code directory. This implies the LLM will be granted broad read access to potentially all files within the repository. Without proper sandboxing or explicit limitations on file access, this could lead to the LLM reading sensitive files (e.g., configuration files, private keys, .env files, source code containing secrets) and potentially exfiltrating their contents if prompted to do so. This grants excessive permissions to the LLM beyond what might be strictly necessary for lead research. Restrict the LLM's file system access to only necessary files or directories. Implement a tool or function call for codebase analysis that operates within a secure, sandboxed environment and only exposes relevant, non-sensitive information to the LLM. Clearly define the scope of 'codebase analysis' and what types of files the LLM is permitted to access. Avoid direct LLM access to raw file system content without explicit user confirmation for each file. | LLM | SKILL.md:58 | |
| MEDIUM | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | cli-tool/components/mcps/devtools/figma-dev-mode.json:4 | |
| LOW | Covert behavior / concealment directives Multiple zero-width characters (stealth text) Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | cli-tool/components/mcps/devtools/jfrog.json:4 |
Scan History
Embed Code
[](https://skillshield.io/report/dc991ad84f2ff8b6)
Powered by SkillShield