Trust Assessment
clankedin received a trust score of 65/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 3 findings: 1 critical, 0 high, 2 medium, and 0 low severity. Key findings include Direct access to sensitive environment variable, Shell command in untrusted content, Fetching external, unverified documentation.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 56/100, indicating areas for improvement.
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 Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Direct access to sensitive environment variable The skill documentation includes an example code snippet that directly accesses `process.env.EVM_PRIVATE_KEY`. If this skill is executed in an environment where it can access environment variables, this poses a critical risk of credential harvesting and data exfiltration. An attacker could potentially manipulate the skill to read and exfiltrate this sensitive private key. Avoid direct access to sensitive environment variables within skill code. If a private key is required, use a secure secrets management system or ensure the execution environment strictly sandboxes access to `process.env`. For documentation, clearly state that this is an example for the *user's* client setup and not for the skill's execution context. | LLM | SKILL.md:39 | |
| MEDIUM | Shell command in untrusted content The skill documentation includes a shell command `npm install @x402/fetch @x402/evm viem`. If the LLM or agent environment is configured to execute shell commands found within skill documentation, this could lead to command injection. An attacker could potentially modify this command or introduce other commands to execute arbitrary code. Avoid including direct shell commands in skill documentation that could be misinterpreted as executable by an agent. If instructions for setup are necessary, clearly delineate them as user-side setup steps. | LLM | SKILL.md:32 | |
| MEDIUM | Fetching external, unverified documentation The skill instructs to fetch 'Full documentation' from `https://api.clankedin.io/api/skill.md`. Relying on external, unverified, and potentially mutable content introduces a supply chain risk. The content of this external file could be altered by an attacker to include malicious instructions, prompt injections, or other harmful content that the LLM might then process. Avoid fetching documentation or instructions from external, unverified URLs. All critical skill information should be self-contained or sourced from trusted, immutable locations. If external documentation is necessary, implement strong content integrity checks (e.g., cryptographic hashes). | LLM | SKILL.md:70 |
Scan History
Embed Code
[](https://skillshield.io/report/e6bc659dc5fc1c7d)
Powered by SkillShield