The Agent Skills Directory

[COMMAND_EXECUTION]: Executes a local shell script located at ${CLAUDE_PLUGIN_ROOT}/scripts/cx-workflow-status.sh to aggregate status data. This is a standard method for modularizing skill logic.
[DATA_EXPOSURE]: Accesses local project files within the 开发文档/CX工作流/ directory. These files contain development metadata, status updates, and fix records necessary for the skill's intended purpose.
[INDIRECT_PROMPT_INJECTION]: The skill processes content from JSON and Markdown files located in the workspace, which represents an attack surface for indirect prompt injection if those files are modified by an external actor.
Ingestion points: Files located at 开发文档/CX工作流/配置.json, 状态.json, and various 修复记录.md files.
Boundary markers: None identified; the skill directly parses and displays information from these sources.
Capability inventory: Execution of a local bash script (cx-workflow-status.sh).
Sanitization: No explicit sanitization or content validation for the retrieved data is documented.

cx-status