Trust Assessment
autofillin received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 8 findings: 3 critical, 0 high, 5 medium, and 0 low severity. Key findings include Arbitrary command execution, Sensitive environment variable access: $HOME, Remote code execution: curl/wget pipe to shell.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Static Code Analysis layer scored lowest at 35/100, indicating areas for improvement.
Last analyzed on February 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings8
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Remote code download piped to interpreter Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/leohan123123/autofillin/scripts/setup-env.sh:133 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/leohan123123/autofillin/scripts/setup-env.sh:133 | |
| CRITICAL | MCP Filesystem Server granted root directory access The skill's `mcpServers` configuration explicitly grants the `@modelcontextprotocol/server-filesystem` tool access to the entire root directory (`/`). This allows the skill to read, write, and delete any file on the system, including sensitive user data, configuration files, and credentials (such as `~/.playwright-auth.json` mentioned in the skill). This excessive permission creates a severe data exfiltration, data tampering, and integrity risk, as the skill can access any part of the filesystem without specific user consent for each access. Restrict the filesystem server's access to the absolute minimum necessary directories. For example, if the skill only needs to access files in a user's 'Downloads' folder or a skill-specific sandbox, specify that directory (e.g., `~/Downloads` or `./data`). Avoid granting root (`/`) access. | LLM | SKILL.md:49 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/leohan123123/autofillin/scripts/autofillin.sh:133 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/leohan123123/autofillin/scripts/setup-env.sh:17 | |
| MEDIUM | Sensitive environment variable access: $USER Access to sensitive environment variable '$USER' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/leohan123123/autofillin/scripts/setup-env.sh:171 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/leohan123123/autofillin/scripts/start-chrome.sh:15 | |
| MEDIUM | Sensitive environment variable access: $USER Access to sensitive environment variable '$USER' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/leohan123123/autofillin/scripts/start-chrome.sh:94 |
Scan History
Embed Code
[](https://skillshield.io/report/e9840252a44dcf21)
Powered by SkillShield