Trust Assessment
clickup-mcp 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 7 findings: 3 critical, 3 high, 1 medium, and 0 low severity. Key findings include File read + network send exfiltration, Sensitive path access: AI agent config, Unpinned external binary dependency.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 10/100, indicating areas for improvement.
Last analyzed on February 12, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings7
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | File read + network send exfiltration AI agent config/credential 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/pvoo/clickup-mcp/SKILL.md:33 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential 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/pvoo/clickup-mcp/SKILL.md:38 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential 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/pvoo/clickup-mcp/SKILL.md:69 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/pvoo/clickup-mcp/SKILL.md:33 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.clawdbot/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/pvoo/clickup-mcp/SKILL.md:38 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/pvoo/clickup-mcp/SKILL.md:69 | |
| MEDIUM | Unpinned external binary dependency The skill relies on the 'mcporter' binary, as indicated by the manifest's `bins` requirement and its usage throughout the setup instructions in `SKILL.md`. However, no specific version or trusted installation method is provided for 'mcporter'. This introduces a supply chain risk, as a user might install a compromised, malicious, or incompatible version of 'mcporter', potentially leading to command injection, data exfiltration, or other security breaches when the skill invokes it. Without version pinning, future updates to 'mcporter' could also introduce breaking changes or vulnerabilities. Specify a pinned version for the 'mcporter' binary dependency, if possible, or provide clear instructions for installing a verified version from a trusted source (e.g., with checksum verification). If 'mcporter' is a package, include version constraints in a `requirements.txt` or similar file. If it's a standalone binary, provide a specific download URL and SHA256 hash. The skill's manifest should ideally include version constraints for its binary dependencies. | LLM | SKILL.md:41 |
Scan History
Embed Code
[](https://skillshield.io/report/0f7450fc624a0ab6)
Powered by SkillShield