Trust Assessment
safe-skills received a trust score of 83/100, 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, Agent required to manage sensitive API key, Skill grants broad financial transaction capabilities.
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/glitch003/safe-skills/SKILL.md:1 | |
| MEDIUM | Agent required to manage sensitive API key The skill design requires the agent to receive, store, and use an `apiKey` for all subsequent authenticated requests. This `apiKey` grants full control over the associated EVM wallet. If the agent's internal state, memory, or logging is not securely managed, this `apiKey` could be exposed, leading to unauthorized access to the user's wallet. The documentation explicitly states "store this securely", but the responsibility for secure handling falls on the agent's implementation. Implement robust secret management practices within the agent, such as using secure memory, avoiding logging of sensitive data, and encrypting stored credentials. Consider using a secure vault service for API keys if the agent's environment is not ephemeral or isolated. | LLM | SKILL.md:30 | |
| MEDIUM | Skill grants broad financial transaction capabilities The skill provides endpoints for transferring native tokens and ERC-20 tokens, and critically, for sending arbitrary EVM transactions (`/api/skills/evm-wallet/send-transaction`). While the documentation mentions a `claimUrl` for users to manage policies, the agent, once authenticated with an `apiKey`, has the capability to initiate these powerful actions. If user policies are not sufficiently restrictive or are misconfigured, a compromised agent or a successful prompt injection could lead to unauthorized and potentially irreversible financial transactions. Emphasize to users the critical importance of configuring strict spending policies via the `claimUrl`. Agents integrating this skill should implement robust input validation and user confirmation mechanisms before executing any financial transaction, especially arbitrary ones. Consider adding a "dry run" or simulation feature to the skill API for arbitrary transactions. | LLM | SKILL.md:90 |
Scan History
Embed Code
[](https://skillshield.io/report/a84324d1c7c83aa5)
Powered by SkillShield