Trust Assessment
clawrag received a trust score of 80/100, 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, Unpinned npm package dependency, Unpinned Git repository dependency.
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/2dogsandanerd/clawrag/SKILL.md:1 | |
| MEDIUM | Unpinned npm package dependency The skill instructs the host to execute the `@clawrag/mcp-server` npm package via `npx` without specifying a version. This means the latest version will be fetched, which could introduce breaking changes or security vulnerabilities if a future version of the package is compromised or contains malicious code. While the changelog mentions `v1.1.0`, the command itself does not enforce this version. Specify a precise version for the npm package in the `npx` command, e.g., `npx -y @clawrag/mcp-server@1.1.0`, to ensure deterministic behavior and prevent unexpected updates or supply chain attacks. | LLM | SKILL.md:29 | |
| MEDIUM | Unpinned Git repository dependency The skill instructs the user to clone the `ClawRag` repository from GitHub without specifying a particular commit hash or tag. This means the user will always get the latest state of the default branch, which could change over time, potentially introducing breaking changes or security vulnerabilities if the repository is compromised or updated with malicious code. Instruct users to clone a specific version (e.g., a release tag or commit hash) of the repository, for example, `git clone --branch v1.2.0 https://github.com/2dogsandanerd/ClawRag.git` or `git clone https://github.com/2dogsandanerd/ClawRag.git && cd ClawRag && git checkout <commit_hash>`. | LLM | SKILL.md:19 |
Scan History
Embed Code
[](https://skillshield.io/report/711c031e31b34343)
Powered by SkillShield