The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to perform file system modifications and execute shell commands within the project environment.
Evidence: Instructions in SKILL.md (Step 6) and references/lab-page.md direct the agent to "Delete the lab folder" and "Run the type check or build" to clean up the environment. This involves potentially destructive file system operations based on user-provided component paths.
[INDIRECT_PROMPT_INJECTION]: The skill analyzes external data including project source code and rendered component content, which presents a surface for instructions embedded in data to influence the agent.
Ingestion points: The agent reads project-specific files like design tokens, typography scales, and component source code as specified in SKILL.md (Step 1) and references/checks.md.
Boundary markers: There are no explicit instructions to use delimiters or ignore instructions embedded within the analyzed project files.
Capability inventory: The agent has permissions to write to the file system (creating lab pages), modify existing application code (applying fixes), and execute shell scripts (build/type checks).
Sanitization: No sanitization or validation protocols are defined for the project-level data ingested during the review process.

ui-review