The Agent Skills Directory

[COMMAND_EXECUTION]: The skill triggers the execution of a local Node.js script at ".aiox-core/development/scripts/generate-greeting.js" to initialize the agent persona. This script is part of the vendor-managed project structure.
[DATA_EXFILTRATION]: The skill reads project-specific configuration and agent definitions from local directories including ".aiox-core/", ".codex/", and "docs/stories/". No unauthorized data transmission to external domains or access to sensitive system credentials was detected.
[PROMPT_INJECTION]: The skill processes user-controlled project story files, which creates a surface for indirect prompt injection.
Ingestion points: Story files located in "docs/stories/".
Boundary markers: Not explicitly defined in the activation protocol or command instructions.
Capability inventory: Local script execution via Node.js.
Sanitization: No explicit validation or sanitization of story content is mentioned before processing.
[SAFE]: No malicious patterns, obfuscation, or unauthorized remote connections were identified. The skill's operations are transparent and align with its stated purpose.

aiox-po