The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the dxs CLI tool (a Datex vendor resource) to perform context gathering and analysis operations.
Evidence: Several steps in SKILL.md instruct the agent to execute shell commands such as dxs source changes, dxs source workitems, and dxs source explore trace with parameters like <ID> and <config_name>.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and process untrusted data from source code diffs and developer comments.
Ingestion points: Code changes and work item comments are retrieved into the agent context via dxs source changes --with-diffs and dxs source workitems --comments.
Boundary markers: The skill instructions do not define specific delimiters or instructions to isolate the retrieved content from the agent's internal logic.
Capability inventory: The skill has the capability to execute shell commands through the dxs CLI and can invoke the impact-analysis skill.
Sanitization: There is no evidence of content sanitization or validation performed on the ingested code or comment data before processing.

branch-code-reviewer