ai-memory-handoff

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions define the use of memory_handoff_accept to fetch handoff blocks containing summaries and next steps from previous interactions.
  • Ingestion points: External data enters the agent context via the memory_handoff_accept tool as described in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or instructions to the LLM to ignore potentially malicious content within the fetched handoff.
  • Capability inventory: The skill utilizes memory management tools (memory_handoff_accept, memory_handoff_begin, memory_handoff_cancel).
  • Sanitization: There is no evidence of sanitization or content validation for the fetched handoff data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 08:42 PM
Security Audit — agent-trust-hub — ai-memory-handoff