turbo-doctor
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to executegoldskyCLI commands for pipeline diagnostics and management. - Evidence includes commands like
goldsky project list,goldsky turbo list,goldsky turbo logs,goldsky turbo restart, andgoldsky turbo delete. - The skill follows a strict diagnostic workflow and requires user confirmation before executing potentially destructive actions like
deleteorrestart --clear-state. - [INDIRECT_PROMPT_INJECTION]: The skill processes pipeline logs which are derived from external data sources and processing errors, creating an attack surface for indirect prompt injection.
- Ingestion points: The skill fetches the last 100 lines of logs using
goldsky turbo logs <pipeline-name> --tail 100 2>&1inSKILL.md. - Boundary markers: The instructions do not specify explicit delimiters or "ignore instructions" warnings for the log content being analyzed.
- Capability inventory: The agent has the ability to restart, delete, and redeploy pipelines, as well as interact with secrets via
goldsky secret listandgoldsky secret create. - Sanitization: There are no explicit sanitization or filtering steps mentioned for the log output before analysis.
Audit Metadata