The Agent Skills Directory

[COMMAND_EXECUTION]: The skill defines several optimization commands that utilize cargo and grep for code analysis, testing, and linting within a Rust project environment.
[INDIRECT_PROMPT_INJECTION]: The skill has an inherent vulnerability surface for indirect prompt injection due to its interaction with external project data.
Ingestion points: The skill reads .rs source files from the src/ directory using Grep and Read tools.
Boundary markers: No explicit boundary markers or instructions to ignore embedded prompts in source code are provided.
Capability inventory: The skill is configured with access to Bash (specifically for cargo commands), as well as Write, Edit, and WebFetch tools.
Sanitization: There is no evidence of sanitization or validation of the ingested source code content before it is processed by the agent.

bevy-ecs-patterns