cio
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches installation and configuration documentation from the official Customer.io GitHub repository (customerio/cio-cli).
- [COMMAND_EXECUTION]: Executes shell commands using the
cioutility for tool initialization and user authentication. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests data from a remote source that could contain malicious instructions. Ingestion points: Data is fetched from
https://raw.githubusercontent.com/customerio/cio-cli/main/README.md. Boundary markers: Absent; the skill does not use delimiters to wrap the fetched external content. Capability inventory: The agent can execute any command provided by thecioCLI and shell. Sanitization: No content validation or filtering is applied to the remote file before it is processed by the agent.
Audit Metadata