Trust Assessment
xmtp-agents received a trust score of 76/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Potential shell command execution in untrusted content, Unpinned dependency in installation instructions.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential shell command execution in untrusted content The `SKILL.md` contains a `npm install` command within a code block. If the AI agent or a system processing this skill documentation is configured to execute shell commands found in untrusted content, this could lead to arbitrary command execution on the host system. This command is presented as an instruction for the user, but could be misinterpreted and executed by an automated agent. Avoid including direct shell commands in documentation that might be interpreted as executable by an automated agent. If commands are necessary, ensure they are clearly marked for human execution only and consider using a safer mechanism for skill installation or setup if the agent is expected to perform it. | LLM | SKILL.md:34 | |
| HIGH | Unpinned dependency in installation instructions The `SKILL.md` provides installation instructions for `@xmtp/agent-sdk` without specifying a version. Installing unpinned dependencies (e.g., `npm install package-name` instead of `npm install package-name@1.2.3`) can lead to supply chain attacks. If a malicious version of the package is published, a user or automated system following these instructions could install it, potentially allowing arbitrary code execution or data exfiltration. Pin the dependency to a specific, known-good version, e.g., `npm install @xmtp/agent-sdk@1.0.0`. Regularly review and update pinned versions to incorporate security fixes. | LLM | SKILL.md:34 |
Scan History
Embed Code
[](https://skillshield.io/report/94184783d7537630)
Powered by SkillShield