pscale-read-only-replica
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
pscaleCLI tool to perform infrastructure management tasks, including creating and deleting database resources. These commands are executed via the shell. - [INDIRECT_PROMPT_INJECTION]: The skill processes JSON output from the PlanetScale API (via
pscalecommands) to determine the state of the infrastructure. - Ingestion points: Data enters the agent's context through the output of
pscale read-only-replica listandpscale read-only-replica showcommands inSKILL.md. - Boundary markers: No explicit delimiters are used to separate CLI output from subsequent instructions.
- Capability inventory: The skill has the capability to modify infrastructure through
pscale create,pscale update, andpscale deletecommands, and execute queries viapscale sqlas detailed inSKILL.md. - Sanitization: The skill recommends defensive programming patterns when accessing JSON fields (e.g., using defaults like
// empty) to handle potentially untrusted or unexpected API responses.
Audit Metadata