skills/vanilla-bar/kernel/handover/Gen Agent Trust Hub

handover

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface identified in the handover generation process.
  • Ingestion points: The skill collects data from the current session's work status, git branch information, user-provided arguments ($ARGUMENTS), and responses to interactive user questions.
  • Boundary markers: The generation instructions do not define explicit delimiters or 'ignore' instructions for the content being processed into the handover file.
  • Capability inventory: The skill performs file system write operations to the .claude/handovers/ directory.
  • Sanitization: There is no evidence of data sanitization, escaping, or validation performed on session context or user input before it is written to the handover document.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 12:05 PM