rudder-data-catalog

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the rudder-cli command-line tool via Bash to interact with workspace data catalog resources. This includes operations to retrieve resource lists, validate YAML schema files, and apply instrumentation changes to the production environment.
  • [PROMPT_INJECTION]: An indirect prompt injection surface exists as the skill instructs the agent to ingest and act upon data from local YAML files.
  • Ingestion points: YAML configuration files located in the data-catalog/ directory and its subdirectories.
  • Boundary markers: Absent; the agent is expected to parse the file content as structured schema data without explicit delimiters or instructions to ignore embedded natural language commands.
  • Capability inventory: The agent has access to shell execution (rudder-cli), and file system operations including Read, Write, and Edit.
  • Sanitization: No sanitization or validation of the file content is performed prior to processing by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 05:31 AM
Security Audit — agent-trust-hub — rudder-data-catalog