Trust Assessment
project-scaffold received a trust score of 45/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 5 findings: 1 critical, 0 high, 4 medium, and 0 low severity. Key findings include File read + network send exfiltration, Missing required field: name, Sensitive path access: Environment file.
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 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings5
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | File read + network send exfiltration .env file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/cmanfre7/project-scaffold/SKILL.md:127 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/cmanfre7/project-scaffold/SKILL.md:1 | |
| MEDIUM | Sensitive path access: Environment file Access to Environment file path detected: '.env.local'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/cmanfre7/project-scaffold/SKILL.md:127 | |
| MEDIUM | Skill provides shell commands for execution The skill provides shell commands under 'Init commands' and 'Post-Scaffold Checklist'. If the host LLM is configured to directly execute these commands, and if any part of the command (e.g., project name) is derived from untrusted user input without proper sanitization, it could lead to command injection. While the examples use static names, the pattern of providing shell commands for execution is a potential vector for abuse. The host LLM should always sanitize any user-provided input before incorporating it into shell commands. It should also prompt for user confirmation before executing any shell commands. Skills should explicitly state if commands are intended for direct execution or as examples. | LLM | SKILL.md:26 | |
| MEDIUM | Unpinned dependencies in recommended installation commands The 'Init commands' for the API/Backend project type suggest installing 'fastapi' and 'uvicorn' without specifying version numbers (`uv pip install fastapi uvicorn`). This means the latest available versions will be installed. This practice can lead to unexpected breaking changes, security vulnerabilities if a malicious version is published, or inconsistencies across environments. Always pin dependencies to specific versions (e.g., `fastapi==0.104.1 uvicorn==0.24.0`). This ensures reproducibility and reduces the risk of introducing unexpected issues from new package versions. | LLM | SKILL.md:44 |
Scan History
Embed Code
[](https://skillshield.io/report/8dec95fe550406b2)
Powered by SkillShield