Trust Assessment
bankr received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Skill exposes high-privilege financial operations.
The analysis covered 4 layers: dependency_graph, manifest_analysis, llm_behavioral_safety, static_code_analysis. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 15, 2026 (commit 66de0a1e). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Skill exposes high-privilege financial operations The `bankr` skill provides access to a tool that can perform highly sensitive and irreversible financial operations. These include crypto trading, transferring funds, managing NFTs, deploying tokens, and signing/submitting raw blockchain transactions. The skill's manifest and documentation explicitly state these capabilities. While the `SKILL.md` provides extensive safety advice (e.g., dedicated agent wallets, read-only API keys, IP whitelisting), the inherent capabilities granted to an AI agent using this skill are extensive and carry significant risk if the agent is compromised or misused. The `/agent/submit` endpoint, for instance, allows transactions to execute immediately without confirmation, as explicitly warned in the documentation. Implement strict access controls and require explicit user confirmation for all sensitive financial actions. Ensure robust input validation and sanitization for all parameters passed to the `bankr` tool. Encourage users to utilize read-only API keys and dedicated, limited-fund agent wallets for autonomous operations. The LLM should be explicitly aware of the high-risk nature of these operations before invoking them. | Unknown | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/97e866f79e4cb919)
Powered by SkillShield