eo-project-init

Pass

Audited by Gen Agent Trust Hub on May 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs file system operations such as creating directories, moving user-level configuration files during migration, and establishing symbolic links to connect external vaults (e.g., Obsidian) to the project repository.
  • [PROMPT_INJECTION]: The skill ingests user-provided PRD or MVP documents to derive project roadmaps, which introduces an indirect prompt injection surface.
  • Ingestion points: PRD/MVP documents provided as input during the initialization process.
  • Boundary markers: No explicit boundary markers or isolation instructions are used for the ingested content.
  • Capability inventory: The skill can create directories, write project files, and modify agent configuration files (e.g., CLAUDE.md).
  • Sanitization: No sanitization is performed on the ingested content before it is parsed into the project roadmap.
Audit Metadata
Risk Level
SAFE
Analyzed
May 24, 2026, 04:06 AM
Security Audit — agent-trust-hub — eo-project-init