Trust Assessment
wilma-triage 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 Unpinned Dependencies.
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
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Unpinned Dependencies The skill specifies dependencies (`wilma` and `gog` skills) to be installed via `clawhub` without specifying a version. This can lead to non-deterministic builds, unexpected behavior, or introduce vulnerabilities if a future version of the dependency contains malicious code or breaking changes. It is a common supply chain risk. Specify exact versions for all dependencies (e.g., `clawhub install wilma@1.0.0`) or use a lock file mechanism if `clawhub` supports it, to ensure deterministic and secure dependency resolution. | LLM | SKILL.md:7 | |
| MEDIUM | Unpinned Dependencies The skill specifies dependencies (`wilma` and `gog` skills) to be installed via `clawhub` without specifying a version. This can lead to non-deterministic builds, unexpected behavior, or introduce vulnerabilities if a future version of the dependency contains malicious code or breaking changes. It is a common supply chain risk. Specify exact versions for all dependencies (e.g., `clawhub install gog@1.0.0`) or use a lock file mechanism if `clawhub` supports it, to ensure deterministic and secure dependency resolution. | LLM | SKILL.md:8 |
Scan History
Embed Code
[](https://skillshield.io/report/aceed6145848492f)
Powered by SkillShield