fileset-cli

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill utilizes the filesets query command to perform AI-powered semantic searches over the content of files stored in Domo FileSets. This represents an ingestion point for untrusted external data. While intended for search, malicious content within these files could attempt to influence the agent's reasoning or behavior if the output is not properly delimited or if the agent lacks specific instructions to ignore embedded commands.
  • Ingestion points: Ingests file content from Domo FileSets via community-domo-cli filesets query (SKILL.md).
  • Boundary markers: None identified in the provided instructions to separate data from instructions.
  • Capability inventory: The skill uses community-domo-cli which supports file downloads (write), uploads (read), and metadata retrieval.
  • Sanitization: No explicit sanitization or validation of the retrieved file content is described.
  • [COMMAND_EXECUTION]: The skill relies on the execution of shell commands through the community-domo-cli tool. It explicitly documents capabilities for local file system interaction, including downloading binary files to arbitrary local paths (--output <path>) and uploading local files to the Domo cloud. These operations are core to the skill's purpose but involve significant file system access.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 06:14 PM