The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run git diff to identify code changes and npm test to verify that code refinements preserve existing functionality. These are standard, expected operations for a developer-focused tool.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data in the form of git diffs and source code files, creating a potential surface for indirect prompt injection if those files contain malicious instructions.
Ingestion points: Output from git diff and the content of modified files (SKILL.md).
Boundary markers: No specific delimiters or safety instructions are defined to separate ingested code from the agent's instructions.
Capability inventory: Git command execution, npm command execution, and file modification (SKILL.md).
Sanitization: No explicit sanitization or filtering of the processed code content is described.

slop