community-cli-howto
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the community-domo-cli tool from the author's GitHub repository and the official ryuu CLI from the npm registry.
- [COMMAND_EXECUTION]: Provides a comprehensive list of shell commands for the agent to manage Domo datasets, AppDB collections, and filesets.
- [DATA_EXFILTRATION]: Documents the location of sensitive authentication data at ~/.config/configstore/ryuu/, noting that the CLI tool reuses credentials from this path.
- [PROMPT_INJECTION]: The skill processes external data through command-line arguments and file inputs, which represents an indirect prompt injection surface.
- Ingestion points: Data is ingested via --body and --body-file arguments in SKILL.md for operations like SQL execution and file uploads.
- Boundary markers: None present; the instructions do not include delimiters or specific warnings for the agent regarding the contents of these files.
- Capability inventory: Shell command execution capabilities across datasets, appdb, and filesets modules.
- Sanitization: Not explicitly implemented; the skill suggests using a --dry-run flag for manual verification of payloads.
Audit Metadata