pscale-service-token
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONCREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's primary function is to guide the agent in executing
pscaleCLI commands to manage authentication tokens. - [CREDENTIALS_UNSAFE]: The skill facilitates the management of high-privilege service tokens and API tokens used for CI/CD automation. It includes explicit warnings against pasting secrets into chat and provides clear guidance on using environment variables and secrets managers (e.g., GitHub Secrets) to mitigate exposure risks.
- [INDIRECT_PROMPT_INJECTION]: The skill handles data ingested from external sources (PlanetScale API responses) when listing or showing service token metadata.
- Ingestion points: API responses returned from
pscale service-token listandpscale service-token show(SKILL.md, references/commands.md). - Boundary markers: None explicitly defined for isolating tool output within the prompt context.
- Capability inventory: Subprocess execution of the
pscaleCLI across all workflows. - Sanitization: No specific sanitization or filtering of API response content is mentioned before processing.
Audit Metadata