The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external code files and user-provided search/replace patterns as input for the ast_grep_find.py script, creating a potential surface for indirect prompt injection if processing untrusted data.
Ingestion points: The skill reads file content from locations specified by the --path and --glob parameters and processes pattern strings provided via the --pattern argument.
Boundary markers: There are no explicit boundary markers, delimiters, or instructions provided to the agent to disregard instructions potentially embedded within the code being analyzed.
Capability inventory: The skill utilizes the Bash tool to execute Python scripts that perform file system reads and modifications.
Sanitization: The skill instructions do not specify any sanitization, validation, or escaping of the patterns or the content of the files being searched.
[COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands through uv run python to carry out code analysis and refactoring operations.

ast-grep-find