Trust Assessment
opengraph-io received a trust score of 86/100, 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 Unpinned npm 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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Unpinned npm dependency in installation instructions The skill instructs users to install and run the `opengraph-io-mcp` npm package using `npx` without specifying a version. This means `npx` will always fetch the latest version from the npm registry. If a malicious update is published to `opengraph-io-mcp`, users following these instructions could unknowingly execute compromised code, leading to arbitrary code execution on their system. Pin the version of `opengraph-io-mcp` in the installation instructions (e.g., `npx opengraph-io-mcp@1.4.0`) and in the `clawdbot.json` configuration (`"args": ["-y", "opengraph-io-mcp@1.4.0"]`). Regularly audit the specified version for vulnerabilities and update as needed. | LLM | SKILL.md:178 |
Scan History
Embed Code
[](https://skillshield.io/report/91e05154467b3451)
Powered by SkillShield