Trust Assessment
changenow-earner received a trust score of 89/100, 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, 1 medium, and 2 low severity. Key findings include Suspicious import: requests, Unvalidated user input passed to external API.
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 | Suspicious import: requests Import of 'requests' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Static | skills/yakelb0815/changenow/scripts/swap.py:2 | |
| LOW | Unvalidated user input passed to external API The skill directly interpolates user-provided string arguments (`from_coin`, `to_coin`, `address`) into API request URLs and JSON payloads without explicit validation or sanitization. If the ChangeNOW API is vulnerable to injection attacks (e.g., SQL injection, command injection in their backend), a malicious user could craft inputs to manipulate the remote API's behavior. The resulting API response, if fed back to the host LLM, could then act as a prompt injection or lead to data exfiltration from the remote service. Implement explicit validation for `from_coin`, `to_coin`, and `address` arguments (e.g., regex for allowed characters, length checks, or a whitelist of supported coins) before constructing API requests. This mitigates the risk of injection attacks against the remote API and subsequent prompt injection to the host LLM. | LLM | scripts/swap.py:10 | |
| LOW | Unvalidated user input passed to external API The skill directly interpolates user-provided string arguments (`from_coin`, `to_coin`, `address`) into API request URLs and JSON payloads without explicit validation or sanitization. If the ChangeNOW API is vulnerable to injection attacks (e.g., SQL injection, command injection in their backend), a malicious user could craft inputs to manipulate the remote API's behavior. The resulting API response, if fed back to the host LLM, could then act as a prompt injection or lead to data exfiltration from the remote service. Implement explicit validation for `from_coin`, `to_coin`, and `address` arguments (e.g., regex for allowed characters, length checks, or a whitelist of supported coins) before constructing API requests. This mitigates the risk of injection attacks against the remote API and subsequent prompt injection to the host LLM. | LLM | scripts/swap.py:18 |
Scan History
Embed Code
[](https://skillshield.io/report/88207658b559ccdc)
Powered by SkillShield