dialpad
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npx @useclawlink/cli, which downloads and executes the vendor's command-line interface from the official NPM registry at runtime. This is a standard method for utilizing the vendor's tooling. - [COMMAND_EXECUTION]: The instructions direct the agent to run various shell commands using the
@useclawlink/clito handle authentication, discover actions, and execute Dialpad operations. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill reads external data from Dialpad (e.g., messages or call information) via the
runcommand as described inSKILL.md. - Boundary markers: The skill explicitly instructs the agent to read first and confirm with the user before performing any write operations, providing a human-in-the-loop safety check.
- Capability inventory: The skill possesses the ability to execute shell commands and interact with the Dialpad API through the vendor CLI.
- Sanitization: No explicit programmatic sanitization of the remote data is defined in the instruction file, relying on the agent's internal guardrails and the user confirmation step.
Audit Metadata