The Agent Skills Directory

[PROMPT_INJECTION]: The skill features a surface for indirect prompt injection as it is designed to read and analyze untrusted content from the codebase being explored.
Ingestion points: The skill ingests codebase data using the Read and Grep tools as part of its sub-agent exploration tasks in SKILL.md.
Boundary markers: There are no explicit boundary markers or instructions to ignore potential commands embedded within the analyzed files.
Capability inventory: The skill possesses capabilities including directory creation and file writing via Bash(mkdir *) and Write tools, and command execution through Bash(git *), Bash(ls *), Bash(find *), and Bash(jq *) as defined in the frontmatter and SKILL.md.
Sanitization: The instructions do not specify any content sanitization or validation for the data read from the repository files.

deep-explorer