The Agent Skills Directory

[COMMAND_EXECUTION]: The skill performs local environment analysis using standard system utilities to gather project metadata.
Executes grep to scan for code patterns such as @SaCheckPermission, package names, and TODO tags in the ruoyi-modules/ directory.
Executes git log to extract commit summaries, hashes, and dates for activity reporting.
Uses glob patterns to verify the existence and structure of controller files.
[PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it processes file content from the local environment.
Ingestion points: Content is ingested from .java files and Git history through the output of grep and git commands.
Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore embedded instructions within the source code being scanned.
Capability inventory: Capabilities are restricted to read-only command execution and markdown report generation; no network or file-write operations are defined.
Sanitization: No explicit sanitization or validation of the scanned file content is performed before the agent summarizes the data.

sync