The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes multiple local commands using uv run and uvx, including custom CI scripts (scripts/ci/*.py), ruff, pyright, and pytest. These are standard development workflows for linting and testing.
[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests and processes source code and documentation from the repository.
Ingestion points: Processes all files in src, tests, docs, and website/docs/ through various tools (ruff, pyright, pytest, grep) in SKILL.md.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands in the processed data are present in SKILL.md.
Capability inventory: Can execute arbitrary local scripts via uv run, perform repository-wide searches via grep, and modify files via ruff --fix as defined in SKILL.md.
Sanitization: No explicit sanitization or validation of the content being processed by the underlying tools is documented in the skill.

check