The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted code changes which could contain malicious instructions designed to manipulate the agent's behavior during the simplification process.
Ingestion points: Reads the current code changes and repository history using git diff and git merge-base as described in Workflow Step 1 of SKILL.md.
Boundary markers: The instructions do not define specific delimiters or warnings to prevent the agent from following instructions embedded within the code being analyzed.
Capability inventory: The skill has the capability to execute shell commands, including git operations and the repository's verification suite (tests, linter, and type-checker) as noted in Workflow Step 4.
Sanitization: There is no mention of sanitizing or escaping the content of the code changes before the agent processes them.
[COMMAND_EXECUTION]: The skill requires the agent to execute shell commands to interact with the local git repository and verify code changes.
Evidence: The workflow specifies the use of git merge-base HEAD origin/<default>, git diff HEAD, and git diff --stat. It also explicitly instructs the agent to "Run the repo's tests, typecheck, and lint" following each batch of code cuts.

antfu-simplify