buildkite-migration
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
bkCLI tool using Homebrew from the official Buildkite tap (buildkite/buildkite/bk) or via binary downloads from the official GitHub repository (github.com/buildkite/cli/releases). These are trusted distribution channels for the vendor. - [COMMAND_EXECUTION]: The skill executes shell commands to install the CLI and perform the conversion (
bk pipeline convert). These commands are standard for the migration workflow and use local temporary files for processing. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted CI/CD configuration files provided by users.
- Ingestion points: The agent reads user-provided pipeline files (e.g., Jenkinsfile, GitHub Actions YAML) and the resulting converted output from the local filesystem.
- Boundary markers: The instructions explicitly direct the agent to "display it as a YAML code block — nothing else" and "not summarise, annotate, or critique the output," which prevents the agent from executing instructions that might be embedded in the source or converted files.
- Capability inventory: The skill has access to the
bkCLI and file system read/write operations. - Sanitization: While no explicit sanitization is performed on the input, the strict output formatting instructions mitigate the risk of the agent following malicious instructions within the data.
Audit Metadata