Trust Assessment
xero received a trust score of 88/100, 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 Potential Command Injection via `curl` examples.
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 | Potential Command Injection via `curl` examples The `SKILL.md` file contains several `bash` code blocks demonstrating `curl` commands to interact with the Xero API. These `curl` commands represent direct shell executions. As per the analysis rules, content within the untrusted delimiters is treated as untrusted data. If an AI agent is designed to parse and execute these examples, or generate similar commands based on user input, there is a significant risk of command injection. Specifically, if user-provided data is incorporated into the `curl` command's arguments (e.g., the JSON body for `Create Invoice` or URL query parameters for `Get Profit & Loss Report`) without robust sanitization, an attacker could inject arbitrary shell commands or manipulate the API calls in unintended ways. Ensure that any AI agent executing commands derived from this skill's examples rigorously sanitizes all user-provided input before incorporating it into shell commands. Implement strict allow-listing for parameters and values, and avoid direct concatenation of untrusted input into shell command strings. Consider using dedicated API client libraries instead of raw `curl` commands for safer parameter handling. | LLM | SKILL.md:20 |
Scan History
Embed Code
[](https://skillshield.io/report/a25b7cbfd77c0479)
Powered by SkillShield