moai-project-template-optimizer

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface through its core template processing and merging functionality.
  • Ingestion points: The skill reads and analyzes content from project backups (located in '.moai-backups/'), configuration files ('.claude/settings.json', '.moai/config.json'), and project documentation ('CLAUDE.md').
  • Boundary markers: The instructions for merging and comparing these files do not specify the use of delimiters or explicit 'ignore embedded instructions' warnings, creating a risk that malicious instructions in the processed files could influence the agent.
  • Capability inventory: The skill is authorized to use tools such as 'Read', 'Glob', and 'Grep' to access project files. Documentation also references shell-like operations ('ls', 'find', 'tar') for discovery and extraction.
  • Sanitization: There is no evidence of structural validation or content sanitization for the data being merged from either local project files or external backups.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 05:14 PM