Trust Assessment
playground received a trust score of 87/100, 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, 0 high, 2 medium, and 0 low severity. Key findings include Unpinned npm dependency version, Unsanitized output of user-controlled content to terminal.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Unpinned npm dependency version Dependency 'clawdhub' is not pinned to an exact version ('^0.3.0'). Pin dependencies to exact versions to reduce drift and supply-chain risk. | Dependencies | skills/frodo-temaki/playground/package.json | |
| MEDIUM | Unsanitized output of user-controlled content to terminal The `scripts/connect.js` script directly prints content received from the WebSocket (e.g., agent names, messages, room descriptions) to the console without sanitizing for ANSI escape codes. An attacker in the Playground could send specially crafted messages containing ANSI escape sequences (e.g., `\x1b[...]`) to manipulate the user's terminal, such as clearing the screen, changing colors, or moving the cursor. This could lead to a misleading display, disruption of the interactive session, or a form of 'terminal injection'. Sanitize all user-controlled strings received from the WebSocket before printing them to the console. This can be done by removing or escaping ANSI escape codes using a library like `strip-ansi` or a custom sanitization function. Apply this sanitization to all `console.log` statements that display dynamic content from the Playground, including agent names, message content, room names, and descriptions. | LLM | scripts/connect.js:38 |
Scan History
Embed Code
[](https://skillshield.io/report/f52171e970461831)
Powered by SkillShield