ac-handoff-creator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill captures session context and next actions into a structured JSON package to be loaded by future sessions, creating a bridge for cross-session instruction injection.
  • Ingestion points: Data is ingested from the current session's file modifications, decision logs, and progress summaries (SKILL.md).
  • Boundary markers: No boundary markers or instructions to ignore embedded commands are specified for the 'context' or 'next_actions' JSON fields.
  • Capability inventory: The skill references scripts/handoff_creator.py for execution and integration with state-tracking tools.
  • Sanitization: There is no evidence of sanitization or validation of the text content placed into the handoff package.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:30 PM