Trust Assessment
cwicr-comparison-tool received a trust score of 87/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 0 high, 2 medium, and 0 low severity. Key findings include Missing required field: name, Unrestricted File Write to Arbitrary Path.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| 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/datadrivenconstruction/cwicr-comparison-tool/SKILL.md:1 | |
| MEDIUM | Unrestricted File Write to Arbitrary Path The `export_comparison` function allows writing an Excel file to an arbitrary `output_path` provided by the user. If the input dataframes contain sensitive information, an attacker could specify a path to an accessible location (e.g., a public directory or a location they can retrieve) to exfiltrate data. This also poses a risk of overwriting critical system files if the skill is granted broad write permissions and the path is not properly validated or sandboxed. Implement strict validation and sanitization for `output_path`. Ensure the path is confined to a secure, temporary, or user-specific output directory. Prevent directory traversal attacks (e.g., `../`). The agent environment should enforce strong sandboxing for file write operations to limit the scope of potential damage. | LLM | SKILL.md:313 |
Scan History
Embed Code
[](https://skillshield.io/report/18fc12c04acc33ba)
Powered by SkillShield