skills/thedotmack/claude-mem/handoff/Gen Agent Trust Hub

handoff

Pass

Audited by Gen Agent Trust Hub on Sep 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes session history and memory observations to generate a local documentation file, creating a surface for persisting conversation data.
  • Ingestion points: Conversation history and agent memory (via claude-mem tools) are used as data sources in SKILL.md.
  • Boundary markers: The skill uses a structured Markdown template to organize the handoff information, though it does not explicitly sanitize data within those sections.
  • Capability inventory: The skill utilizes file system write access for HANDOFF.md and reads from session memory tools.
  • Sanitization: No explicit sanitization or filtering is applied to the session data before it is written to the file.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 30, 2026, 03:39 PM