aile-docs-init
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to inspect the project environment and manage directories. Evidence includes the use of
ls,find,git log, andmkdirinSKILL.mdfor project discovery and documentation structure creation. - [EXTERNAL_DOWNLOADS]: The skill integrates with an external Google Drive service to synchronize documentation files to shared folders. Evidence includes the use of a
google-driveskill and specific folder IDs (e.g.,1u2I7QtOQDzWnQAVgINZqQbLv0wOjvR_0) defined indocs-templates/google-drive-sync-integration.md. - [PROMPT_INJECTION]: The skill uses role-play instructions to define the agent's persona and ingests untrusted source code, creating an indirect prompt injection surface.
- Ingestion points: The skill reads local source code files (src/, app/, lib/) and configuration files in
Phase 1B. - Boundary markers: No specific delimiters or 'ignore embedded instructions' warnings are implemented when reading codebase content.
- Capability inventory: Shell execution (
ls,mkdir,find,git), file writing, and remote synchronization via thegoogle-drivetool. - Sanitization: There is no evidence of sanitization or filtering of the content extracted from the codebase before processing.
Audit Metadata