The Agent Skills Directory

[PROMPT_INJECTION]: The skill contains instructions to read and incorporate guidance from local repository files, creating a surface for indirect prompt injection.
Ingestion points: Workflow Step 2 in SKILL.md and references/bootstrap.md (Steps 3 and 5) direct the agent to inspect AGENTS.md, CLAUDE.md, or other local rules files.
Boundary markers: The instructions do not specify boundary markers or provide warnings to disregard instructions embedded within these external files.
Capability inventory: The skill allows the agent to modify critical repository configuration files (e.g., package.json, CI workflows) and execute vp toolchain commands.
Sanitization: There is no mention of sanitizing or validating the contents of the guidance files before the agent follows their instructions.
[EXTERNAL_DOWNLOADS]: The skill references and integrates an external GitHub Action for CI/CD setup.
Evidence: SKILL.md and references/ci-cd.md recommend using voidzero-dev/setup-vp@v1 for automating environment setup and caching.
[COMMAND_EXECUTION]: The skill relies on the execution of the vp CLI tool for various operations including environment setup, package installation, and upgrading the tool itself.
Evidence: Various files (e.g., SKILL.md, references/commands.md) use commands such as vp install, vp check, vp test, vp upgrade, and vp update to perform migration and validation tasks.

viteplus