The Agent Skills Directory

[SAFE]: The skill performs legitimate project development tasks by following steps defined in local plan files. No unauthorized file access or network operations were identified.
[SAFE]: No hardcoded credentials or obfuscated code were found in the skill definitions.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes external files to determine its implementation steps.
Ingestion points: Reads plano-fluig-*.md files to extract implementation steps.
Boundary markers: Not present; the skill treats all content in the plan files as instructions to be followed sequentially.
Capability inventory: Possesses the ability to create and modify files, and activate other project-related agent skills.
Sanitization: No sanitization or safety validation of the plan file content is mentioned or performed.

fluig-exec