The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to scan arbitrary files within the codebase (such as components, documentation, and brand assets) and synthesize their content into design guidelines. This creates a surface for indirect prompt injection if those files contain malicious instructions.
Ingestion points: Codebase files scanned during Step 1 (README, components, style guides, etc.).
Boundary markers: None provided in the instructions to separate external data from agent instructions.
Capability inventory: File-write operations to .impeccable.md and .github/copilot-instructions.md.
Sanitization: No sanitization or validation of the ingested content is specified before it is written to configuration files.
[COMMAND_EXECUTION]: The skill requires the agent to perform extensive file system operations, including reading various configuration and source files and writing to persistent instruction files in the project root and .github directory.

teach-impeccable