The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is intended to process and simplify code changes, which serves as an ingestion point for untrusted data that could contain malicious instructions.
Ingestion points: The skill instructs the agent to inspect code changes and repository files, such as SKILL.md and files within the languages/ directory.
Boundary markers: There are no instructions provided to the agent to use delimiters or specifically ignore instructions embedded within the code changes being processed.
Capability inventory: The instructions imply the agent has the capability to read repository files and potentially run validation tools, though no specific tools are explicitly granted in the frontmatter.
Sanitization: The skill does not include guidelines for sanitizing or escaping the content of the code files before they are processed by the agent.

code-simplifier