skills/justyannicc/skills/handoff/Gen Agent Trust Hub

handoff

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates as a high-level instructional framework for state preservation and task transition. It does not include executable code, external scripts, or network operations.
  • [DATA_EXPOSURE]: The skill promotes secure data handling by instructing the agent to remove credentials, secrets, and personal data from handoff packages and to use authorized protected sources instead of copying sensitive content.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external "canonical sources" and "authoritative records" to construct handoff contracts. This ingestion surface is managed by instructions to distinguish between facts and assumptions and to preserve original wording for later verification.
  • Ingestion points: SKILL.md (Process Step 1: "Read authoritative records before the conversation summary", "bind only the supplied canonical sources").
  • Boundary markers: SKILL.md (Process Step 1: "Mark facts, accepted decisions, assumptions, and unknowns distinctly").
  • Capability inventory: Logic-based state management; no bundled scripts or network tools.
  • Sanitization: SKILL.md (Process Step 3: "Remove credentials, secrets, access tokens, and personal data").
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 05:15 PM