The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands like ls and git diff to detect the workspace environment and determine the depth of the code audit based on changes.
[DYNAMIC_EXECUTION]: A bash script in SKILL.md sources an external configuration script (read-config.sh) from a relative path (../../stelow-workflow-orchestrator/). While this creates a dependency on the external file structure of the vendor's ecosystem, it is consistent with the skill's role within the stelow suite.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted source code. This represents a vulnerability surface where malicious instructions hidden in the analyzed code (e.g., in comments or boilerplate) could attempt to influence the subagent's critique report.
Ingestion points: Source code files discovered in the user-provided {INPUT_PATH}.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands were identified.
Capability inventory: File system read access for analysis and write access to generate a report in the .stelow-codebase-critique/ directory.
Sanitization: No explicit sanitization of the input code content was identified.

stelow-workflow-codebase-critique