bun-monorepo
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies and processes data from external project files to manage workspace catalogs and release scripts.
- Ingestion points: The skill reads
package.jsonfiles frompackages/*/,apps/*/, and the root directory, as well as GitHub workflow files in.github/workflows/. - Boundary markers: No specific boundary markers or instructions to ignore embedded prompts are defined for the ingested data.
- Capability inventory: The skill utilizes shell commands (
jq,grep,git,gh), Bun CLI commands (bun publish,bun patch), and file system write operations through custom scripts. - Sanitization: No explicit sanitization or validation of the input manifests is specified, relying on standard JSON parsing and Bun CLI behavior.
- [DYNAMIC_EXECUTION]: The skill generates and executes custom TypeScript and JavaScript scripts (
scripts/write-changesets-output.tsandscripts/resolvePublishManifests.mjs) to automate release metadata management and manifest resolution. This behavior follows standard development patterns for monorepo tooling.
Audit Metadata