Trust Assessment
doc-pipeline received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Skill requests excessive 'code_execution' and 'computer' permissions.
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 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Skill requests excessive 'code_execution' and 'computer' permissions The skill's manifest declares 'code_execution' and 'computer' as required tools. While 'file_operations' is justified for a document processing skill, 'code_execution' grants the ability to run arbitrary code, and 'computer' provides broad system access. These permissions are excessive for the described functionality of building document processing pipelines and could be exploited for command injection or other malicious activities if not strictly sandboxed or if user input is used to define executable operations. The skill's example Python implementation uses 'Callable' for pipeline stages, which, if derived from untrusted input, could lead to arbitrary code execution given these broad permissions. Review and restrict the declared tools to the minimum necessary for the skill's functionality. If 'code_execution' is truly required, ensure all execution paths are strictly sandboxed, validated, and do not allow arbitrary user-controlled code execution. Provide clear documentation on why these broad permissions are necessary. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/11249def3951c429)
Powered by SkillShield