The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes basic shell commands for environment discovery and directory management. Evidence: Phase 0.1 and Phase 4.1 execute ls -la, git log, and mkdir -p to verify project structures and initialize documentation directories.
[DATA_EXFILTRATION]: The skill facilitates the synchronization of documentation to external cloud storage via the google-drive tool. Evidence: Phase 4.9 and the google-drive-sync-integration.md template define workflows for uploading specifications to hardcoded folder IDs (1u2I7QtOQDzWnQAVgINZqQbLv0wOjvR_0, 12nxdtruC9WtZlDRL58SCxb0BuWUSibqv) corresponding to specific organizational drives. The skill mandates user confirmation for target directories when project attribution is ambiguous.
[PROMPT_INJECTION]: The skill processes user-supplied code to generate technical documentation, which constitutes an indirect injection surface. Evidence: 1. Ingestion points: Local source code files analyzed in Phase 1B. 2. Boundary markers: Not explicitly defined in the analysis prompts. 3. Capability inventory: File system modification, shell command execution, and Google Drive upload capabilities. 4. Sanitization: No explicit sanitization or filtering logic is provided for data extracted from code comments or structure. This behavior is considered safe as it is essential to the skill's primary purpose.

aile-docs-init