The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from git diffs and repository files, creating a surface for indirect prompt injection if those files contain instructions meant to manipulate the agent.
Ingestion points: Git diff output and repository source code files accessed during review.
Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands within the code being analyzed.
Capability inventory: Executes shell commands via subprocess calls (git diff, npm test) and performs file analysis.
Sanitization: No sanitization or escaping is performed on the code content before analysis.
[COMMAND_EXECUTION]: The skill utilizes standard development commands to perform its tasks.
Evidence: Uses git diff to extract code changes and npm test to verify that refinements do not break existing functionality. This is standard behavior for code quality tools.

slop