moai-session-info

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Employs the Bash tool to execute system diagnostic commands and Git operations for state retrieval.
  • [PROMPT_INJECTION]: Exhibits a surface for indirect prompt injection by processing untrusted data.
  • Ingestion points: Reads data from Git commit messages and SPEC files located in the .moai/specs/ directory.
  • Boundary markers: Does not implement specific delimiters or 'ignore' instructions to isolate ingested data from the agent's primary prompt.
  • Capability inventory: Possesses Bash, Read, and Glob capabilities which can be leveraged if an injection is successful.
  • Sanitization: Ingested content is not sanitized or validated before being presented in the session status report.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:07 AM