Trust Assessment
agentyard received a trust score of 75/100, 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, 1 high, 2 medium, and 0 low severity. Key findings include Sensitive environment variable access: $GITHUB_TOKEN, Potential Path Traversal in File Creation, GitHub Token Exposed in Git Remote URL.
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 | Potential Path Traversal in File Creation The skill provides instructions to create a directory and file using `mkdir -p agents/your-agent-name` and `echo ... > agents/your-agent-name/index.html`. If `your-agent-name` is derived from untrusted input without proper sanitization, an attacker could inject path traversal sequences (e.g., `../../`) to create directories and write files outside the intended `agents/` directory, leading to arbitrary file system writes. Implement strict input validation and sanitization for `your-agent-name` to prevent path traversal characters (e.g., `/`, `..`, `\`). Ensure that the agent's environment restricts file system operations to a sandboxed directory. | LLM | SKILL.md:250 | |
| MEDIUM | Sensitive environment variable access: $GITHUB_TOKEN Access to sensitive environment variable '$GITHUB_TOKEN' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/gregm711/agentyard/SKILL.md:57 | |
| MEDIUM | GitHub Token Exposed in Git Remote URL The skill instructs the agent to embed the GitHub token directly into the Git remote URL for push access: `git remote set-url origin "https://youragent:${GITHUB_TOKEN}@github.com/gregm711/agentyard.dev.git"`. While this is a functional method for Git authentication over HTTPS, it exposes the token in the Git configuration (`.git/config`), in shell history, and potentially in logs. This increases the risk of the token being inadvertently exfiltrated or discovered if the agent's local environment is compromised or if `git remote -v` output is logged. Recommend using Git credential helpers (e.g., `git config --global credential.helper store` or platform-specific helpers) to securely store and retrieve the token, rather than embedding it directly in the remote URL. Alternatively, use SSH keys for authentication where possible. | LLM | SKILL.md:56 |
Scan History
Embed Code
[](https://skillshield.io/report/bdcc34370c867aa4)
Powered by SkillShield