The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external codebase files for refactoring, which creates a vulnerability surface if the analyzed data contains malicious instructions.
Ingestion points: The skill operates on source code files, design documents, and technical debt lists provided by the user (as seen in SKILL.md and README.md).
Boundary markers: There are no instructions for the agent to use delimiters or to disregard natural language instructions that might be embedded in the code being analyzed (e.g., in comments or documentation).
Capability inventory: The skill is intended to guide an agent with the ability to read project structures and suggest/execute modifications and deletions to the filesystem.
Sanitization: The skill lacks explicit sanitization or validation logic for the content it processes before interpolating it into the agent's decision-making process.

reducing-entropy