dino-shared
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill implements strong security boundaries by explicitly instructing the agent to treat all data from external sources (notes, prompts, CLI output) as untrusted and to never execute instructions found within that data.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the necessary CLI tool (
@dinoxx/dinox-cli) via npm and adding related skills from the author's repository (ryzencool/dinox-cli-skills) via npx. These are standard deployment procedures for this toolset. - [CREDENTIALS_UNSAFE]: The guidance includes security best practices for authentication, specifically warning against requesting users to paste tokens into chat and instead recommending secure methods like shell environment variables or stdin piping.
- [COMMAND_EXECUTION]: The skill defines a clear protocol for write operations, requiring the agent to display the full command and obtain explicit user confirmation before execution, which serves as a safeguard against accidental or unauthorized modifications.
Audit Metadata