retellai
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to use
npxto download and execute the@useclawlink/clipackage from the NPM registry. - [COMMAND_EXECUTION]: The skill relies on shell command execution to perform authentication (
login,connect) and interact with Retell AI resources (run,actions,describe). - [DATA_EXPOSURE]: The skill documentation identifies that credentials for the service are stored locally at
~/.clawlink/credentials.json, which is standard behavior for the specified CLI tool. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it passes natural language user input directly into CLI command arguments (
npx @useclawlink/cli actions retellai "<what you want to do>"); however, the skill explicitly instructs the agent to confirm actions with the user before performing any write operations.
Audit Metadata