claude-handoff

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to construct and execute a shell command using the claude command-line tool to launch background processes.
  • Evidence: The skill specifies using the command claude --bg --name "<descriptive name>" "<handoff summary>" (SKILL.md).
  • [PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface as it summarizes conversation history and user arguments into a prompt for a subsequent agent session.
  • Ingestion points: Processes current conversation context and user-supplied input for the handoff description (SKILL.md).
  • Boundary markers: No specific delimiters or boundary markers are requested for the generated handoff summary.
  • Capability inventory: The skill possesses the capability to execute CLI commands in the background (SKILL.md).
  • Sanitization: The skill explicitly directs the agent to redact sensitive information, such as API keys and passwords, from the summary before launching the new session (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 08:31 AM
Security Audit — agent-trust-hub — claude-handoff