The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes standard system commands (pwd, git rev-parse, ls) to determine the repository root and identify existing documentation. These commands are benign and necessary for its mapping functionality.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes and summarizes the entire contents of a user-provided repository.
Ingestion points: The skill ingests untrusted data from all source files and documentation within the target repository.
Boundary markers: There are no explicit delimiters or instructions provided to the subagent to ignore embedded commands within the analyzed repository files.
Capability inventory: The skill dispatches Agent tool calls and writes generated summaries to the local docs/codebase/ directory.
Sanitization: No sanitization or filtering of the ingested repository content is performed before it is processed by the subagent.

repo-mapper