Trust Assessment
cwicr-historical-cost received a trust score of 83/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 3 findings: 0 critical, 0 high, 3 medium, and 0 low severity. Key findings include Missing required field: name, Unrestricted file export capability, Unrestricted database save capability.
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 Findings3
| 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-historical-cost/SKILL.md:1 | |
| MEDIUM | Unrestricted file export capability The `export_historical_data` method allows writing the skill's data to an arbitrary file path (`output_path`) provided by the caller. If an LLM agent or user provides an untrusted path, this could lead to overwriting sensitive system files, writing to unauthorized locations, or exfiltrating data by saving it to a publicly accessible directory. Implement strict path validation and sanitization for `output_path`. Restrict file write operations to a designated, secure directory (e.g., a sandbox or temporary directory) and prevent writing to arbitrary system paths. Avoid allowing untrusted input to directly control file paths. | LLM | SKILL.md:250 | |
| MEDIUM | Unrestricted database save capability The `save_database` method allows writing the skill's internal database to an arbitrary file path (`filepath`) provided by the caller. If an LLM agent or user provides an untrusted path, this could lead to overwriting sensitive system files, writing to unauthorized locations, or exfiltrating data by saving it to a publicly accessible directory. Implement strict path validation and sanitization for `filepath`. Restrict file write operations to a designated, secure directory (e.g., a sandbox or temporary directory) and prevent writing to arbitrary system paths. Avoid allowing untrusted input to directly control file paths. | LLM | SKILL.md:288 |
Scan History
Embed Code
[](https://skillshield.io/report/8d752fd446802541)
Powered by SkillShield