Trust Assessment
mcp-builder received a trust score of 85/100, 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 external documentation fetched from mutable branch.
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 20, 2026 (commit e36d6fd3). 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 | Unpinned external documentation fetched from mutable branch The skill instructs the host LLM to fetch documentation from `https://raw.githubusercontent.com/.../main/README.md`. Fetching resources from the `main` branch means the content is not pinned to a specific version or commit hash and can change at any time. A compromise of the upstream repository could lead to the LLM loading malicious or misleading instructions/content, which could then be interpreted and acted upon by the LLM, posing a supply chain risk. Pin the fetched resources to a specific commit hash or version tag (e.g., `https://raw.githubusercontent.com/.../commit_hash/README.md` or `.../v1.2.3/README.md`) to ensure immutability and prevent unexpected changes. | LLM | SKILL.md:100 | |
| MEDIUM | Unpinned external documentation fetched from mutable branch The skill instructs the host LLM to fetch documentation from `https://raw.githubusercontent.com/.../main/README.md`. Fetching resources from the `main` branch means the content is not pinned to a specific version or commit hash and can change at any time. A compromise of the upstream repository could lead to the LLM loading malicious or misleading instructions/content, which could then be interpreted and acted upon by the LLM, posing a supply chain risk. Pin the fetched resources to a specific commit hash or version tag (e.g., `https://raw.githubusercontent.com/.../commit_hash/README.md` or `.../v1.2.3/README.md`) to ensure immutability and prevent unexpected changes. | LLM | SKILL.md:105 |
Scan History
Embed Code
[](https://skillshield.io/report/212811d2ecc0c486)
Powered by SkillShield