connectors-describe
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
airbyte-agentCLI tool to describe connector entities and actions. This is the primary function of the skill and uses the vendor's official toolset. - [EXTERNAL_DOWNLOADS]: The documentation references the installation of the
airbyte-agentCLI via the official Airbyte Homebrew tap (airbytehq/tap/airbyte-agent) and provides a link to the project's official GitHub repository (github.com/airbytehq/airbyte-agent-cli). These are trusted vendor resources. - [INDIRECT_PROMPT_INJECTION]: The skill functions by ingesting metadata (entity names, action types, and field schemas) from external Airbyte connectors.
- Ingestion points: Output from the
airbyte-agent connectors describecommand. - Boundary markers: None explicitly defined in the provided instructions.
- Capability inventory: Subsequent use of
airbyte-agent connectors executebased on discovered metadata. - Sanitization: Not explicitly handled within the skill logic; the agent relies on the CLI tool's output structure. This represents a standard surface for indirect prompt injection common to data discovery tools.
Audit Metadata