handoff

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it summarizes conversation history which may contain untrusted input.
  • Ingestion points: Processes current conversation history and user-provided arguments in SKILL.md.
  • Boundary markers: Lacks instructions for using delimiters to isolate untrusted content in the generated handoff document.
  • Capability inventory: The skill is authorized to write summary files to the filesystem at ~/.hermes/handoffs/ or /tmp.
  • Sanitization: Instructions are provided to manually redact secrets and PII, though automated validation is not specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 10:26 AM