adding-workspace-apps
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes processing user requests from external sources such as Slack, Telegram, and Dispatch chat to generate new workspace applications.
- Ingestion points: User asks originating from Dispatch chat, @agent-native in Slack, or Telegram (SKILL.md).
- Boundary markers: None explicitly mentioned for user-supplied data.
- Capability inventory: The skill facilitates file system writes (scaffolding
apps/<app-name>), command execution (pnpm exec agent-native create), and database operations (Drizzle ORM). - Sanitization: The skill relies on the underlying
agent-nativeframework for sanitization and does not provide specific implementation logic for input filtering. - [COMMAND_EXECUTION]: The instructions reference the use of the
agent-nativeCLI tool to scaffold new projects viapnpm exec agent-native create. This is standard functionality for the intended development workflow. - [DATA_EXPOSURE_AND_EXFILTRATION]: The skill promotes secure practices by instructing users to avoid hardcoding secrets in code or
.envfiles, recommending the framework's workspace-wide vault instead. It also explicitly forbids hardcoding local development ports (e.g., 127.0.0.1, 8080) to prevent environment-specific vulnerabilities.
Audit Metadata