Trust Assessment
basecred received a trust score of 88/100, 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 dependency in installation instructions, Broad .env file search 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 14, 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 | Unpinned dependency in installation instructions The `SKILL.md` instructs users to install `basecred-sdk` without specifying a version (`npm i basecred-sdk`). This can lead to non-deterministic builds and potential supply chain vulnerabilities if a future version of the package introduces breaking changes, security flaws, or malicious code. It's best practice to pin dependencies to a specific version or version range. Pin the dependency to a specific version or version range (e.g., `npm i basecred-sdk@1.2.3` or `npm i basecred-sdk@^1.0.0`) to ensure consistent and secure installations. | LLM | SKILL.md:10 | |
| MEDIUM | Broad .env file search path The `scripts/query.mjs` script's `loadDotEnv()` function searches for `.env` files by walking up to 5 parent directories from the current working directory (`process.cwd()`). This broad search path could lead to the skill reading `.env` files located outside its immediate intended scope, potentially exposing sensitive environment variables from the host system or other projects if they are present in parent directories. While the script only sets variables if they don't already exist, the act of reading the file content itself is an excessive permission. Restrict the `.env` file search to a more specific and controlled location, such as the skill's root directory or a designated workspace root, rather than walking up arbitrary parent directories. Consider using a dedicated environment variable management library that allows explicit configuration of `.env` file paths. | LLM | scripts/query.mjs:30 |
Scan History
Embed Code
[](https://skillshield.io/report/fdeed9358f27aa26)
Powered by SkillShield