voicestudio-maintainer
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the
bunpackage manager for dependency installation, environment setup, and running test suites as part of the development workflow. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from GitHub issues and pull requests while performing maintenance tasks.
- Ingestion points: Contributor pull requests and GitHub issue reports described in the maintenance workflow.
- Boundary markers: Explicit instructions to follow repository-specific policies (AGENTS.md, CLAUDE.md) and a clear statement that installation does not grant authorization for merges, releases, or issue closures.
- Capability inventory: Execution of shell commands via
bunand extensive filesystem read access to the repository structure. - Sanitization: No specific input sanitization or filtering mechanisms are defined for processing external issue or pull request content.
Audit Metadata