skills/neg0diay/skills/claude-handoff/Gen Agent Trust Hub

claude-handoff

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The agent is instructed to launch background processes using the claude command-line tool.
  • Evidence: Template string claude --bg --name "<descriptive name>" "<handoff summary>" in SKILL.md.
  • [DATA_EXFILTRATION]: The instructions suggest referencing external resources via URL in the handoff documentation.
  • Evidence: "Reference them by path or URL instead" in SKILL.md.
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as a bridge for conversation state between agents, creating an attack surface for instructions embedded in history to influence subsequent sessions.
  • Ingestion points: The entire conversation history and user-provided arguments are used to generate the summary.
  • Boundary markers: No specific delimiters are required for the handoff summary content.
  • Capability inventory: Shell command execution via the claude --bg command.
  • Sanitization: The skill provides specific instructions to redact sensitive credentials and PII.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 01:37 PM
Security Audit — agent-trust-hub — claude-handoff