Trust Assessment
self-funding-setup 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 Excessive filesystem permissions declared.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Excessive filesystem permissions declared The skill's manifest declares broad filesystem permissions including 'Read', 'Write', 'Edit', 'Glob', and 'Grep'. While the skill's workflow describes writing specific configuration files (`.uniswap/x402-config.json`, `.well-known/x402-manifest.json`), the 'Write' permission is not scoped to these paths. Furthermore, 'Read', 'Edit', 'Glob', and 'Grep' are not explicitly justified by any described action in the skill's workflow. This broad, unconstrained filesystem access could be exploited by a malicious prompt to read, modify, or delete arbitrary files, or to exfiltrate sensitive data from the agent's environment. Restrict filesystem permissions to the absolute minimum required. If only specific files need to be written, use a more granular permission (e.g., `Write(path='...')`) if the underlying tool supports it. Remove 'Read', 'Edit', 'Glob', and 'Grep' if they are not strictly necessary for the skill's described operations. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/8b09c8fa202cdef7)
Powered by SkillShield