The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill analyzes external source code using tools like Grep and Read. This creates a surface where malicious instructions embedded in code (e.g., in comments) could influence the agent's behavior.
Ingestion points: Grep, Read, and Glob are used to ingest file content in SKILL.md.
Boundary markers: There are no instructions to the agent to ignore potentially malicious content within the code it reads.
Capability inventory: The skill utilizes Edit, MultiEdit, and Bash to modify the codebase and execute validation commands.
Sanitization: No input sanitization or validation logic is defined for the ingested data.
[COMMAND_EXECUTION]: The skill uses the Bash tool to perform environment discovery and run code analysis scripts. It also suggests running build and test commands (e.g., npm test, eslint, claudekit), which are standard for the tool's purpose but involve executing commands on the local system.

refactoring-expert