The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to triage and review external contributions, which creates an attack surface for indirect prompt injection.
Ingestion points: GitHub issues, pull request descriptions, and contributor-submitted code diffs.
Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands in the processed data.
Capability inventory: The agent is instructed to execute shell commands (via bun) and modify the filesystem during triage.
Sanitization: There are no instructions for sanitizing or validating external input before processing.
[COMMAND_EXECUTION]: The skill specifies the use of the 'bun' runtime to manage the project environment and run development tasks.
Evidence: Commands include bun install, bun run dev, bun run test, and bun run dist.
Risk: These commands execute scripts defined in the repository's configuration files (e.g., package.json), which could be maliciously modified if a contributor's branch is checked out for review without proper isolation.

voicestudio-maintainer