The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill sources a shell script from a relative path (../../stelow-product-orchestrator/references/cli-tools/read-config.sh) to access shared configuration logic and functions within the vendor's ecosystem. This executes code stored outside the skill's own package directory.
[INDIRECT_PROMPT_INJECTION]: The skill processes arbitrary source code from user-specified directories, creating a surface for instructions embedded in the data to influence the agent's behavior.
Ingestion points: Files discovered using the find command in the {INPUT_PATH} directory.
Boundary markers: Absent; there are no specific instructions or delimiters used to isolate the audited code from the analysis subagent's instructions.
Capability inventory: The skill can read codebase files and write reports to the .stelow-codebase-critique/ directory.
Sanitization: No input validation or content sanitization is performed on the source files before they are passed to the subagent for critique.
[COMMAND_EXECUTION]: The skill runs several standard shell commands (find, ls, git diff, wc, tr) to automate file discovery and check the repository state. These commands operate on paths provided by the user.

stelow-product-codebase-critique