Trust Assessment
cifer-sdk received a trust score of 78/100, 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, 1 high, 1 medium, and 1 low severity. Key findings include Direct use of process.env.PRIVATE_KEY for wallet initialization, Direct filesystem read/write operations, Unpinned npm dependencies in setup instructions.
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 | |
|---|---|---|---|---|
| HIGH | Direct use of process.env.PRIVATE_KEY for wallet initialization The skill's example code directly accesses `process.env.PRIVATE_KEY` to initialize an `ethers.Wallet`. While the skill notes this should be server-side, if the skill is executed in an environment where `process.env` is accessible, this could lead to the private key being used for unauthorized transactions or potentially exfiltrated. This practice bypasses secure credential management and poses a significant risk. The skill should not directly access `process.env.PRIVATE_KEY`. Instead, it should expect a `signer` object to be passed as an argument from the host LLM, which would be responsible for securely managing and providing access to signing capabilities without exposing raw private keys. The example should be modified to show how a pre-configured `signer` is used, rather than how to load a private key. | LLM | SKILL.md:49 | |
| MEDIUM | Direct filesystem read/write operations The skill demonstrates the use of `fs/promises.readFile` and `fs/promises.writeFile` for file encryption and decryption. This grants broad access to the host system's filesystem. If the skill were to be misused or compromised, it could potentially read or write to arbitrary files, leading to data leakage, corruption, or unauthorized modification of system files. The skill should ideally operate within a strictly sandboxed environment where file access is limited to specific, user-provided files or a temporary, isolated directory. If direct file paths are required, they should be passed as arguments from the host LLM and rigorously validated to prevent path traversal attacks. The skill should not assume arbitrary file access. | LLM | SKILL.md:100 | |
| LOW | Unpinned npm dependencies in setup instructions The setup instructions recommend installing `cifer-sdk`, `ethers`, and `dotenv` without specifying exact versions (e.g., `npm install cifer-sdk ethers dotenv`). This practice can lead to non-deterministic builds and introduces a risk of installing vulnerable or malicious versions of these packages if a new version is released with a security flaw or if a package maintainer's account is compromised. Recommend pinning dependency versions in `package.json` or using a lock file (`package-lock.json` or `yarn.lock`) to ensure deterministic and secure dependency resolution. For installation instructions, suggest `npm install cifer-sdk@^X.Y.Z ethers@^A.B.C dotenv@^P.Q.R` or similar, or simply `npm install` after cloning a repository with a lock file. | LLM | SKILL.md:18 |
Scan History
Embed Code
[](https://skillshield.io/report/537afe23ae7d2cd0)
Powered by SkillShield