Trust Assessment
trade-with-taro received a trust score of 56/100, 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: 0 critical, 3 high, 0 medium, and 0 low severity. Key findings include Hardcoded Bearer Token detected, Potential Command Injection via `curl` examples with unsanitized input.
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 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 | |
|---|---|---|---|---|
| HIGH | Hardcoded Bearer Token detected A hardcoded Bearer Token was found. Secrets should be stored in environment variables or a secret manager. Replace the hardcoded secret with an environment variable reference. | Static | skills/byron-mckeeby/trade-with-taro/SKILL.md:62 | |
| HIGH | Hardcoded Bearer Token detected A hardcoded Bearer Token was found. Secrets should be stored in environment variables or a secret manager. Replace the hardcoded secret with an environment variable reference. | Static | skills/byron-mckeeby/trade-with-taro/SKILL.md:67 | |
| HIGH | Potential Command Injection via `curl` examples with unsanitized input The skill provides `curl` command examples that include placeholders for `YOUR_API_KEY`, `agentName`, `agentUrl`, `{tradeId}`, and various fields within JSON bodies (`content`, `topic`, `tags`, `source`). If the agent's runtime directly interpolates untrusted user input or dynamically generated values into these `curl` commands without proper shell escaping or URL encoding, it could lead to command injection. For example, a malicious `YOUR_API_KEY` or `{tradeId}` could break out of the `curl` command and execute arbitrary shell commands on the host system. This risk is heightened in LLM-based agents that might directly translate these examples into executable code. Agents should avoid direct shell execution of commands constructed with interpolated user or dynamic input. Instead, use secure HTTP client libraries (e.g., `requests` in Python, `fetch` in JavaScript) that handle URL encoding, header construction, and JSON serialization safely. If shell execution is strictly necessary, ensure all interpolated variables are rigorously shell-escaped using appropriate functions (e.g., `shlex.quote` in Python) before command execution. | LLM | SKILL.md:41 |
Scan History
Embed Code
[](https://skillshield.io/report/c382daf710070a06)
Powered by SkillShield