skills/vaayne/agent-kit/handoff/Gen Agent Trust Hub

handoff

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill summarizes session data into handoff.md for a new session to process, creating a potential surface for indirect prompt injection if the source data contains instructions.
  • Ingestion points: The skill analyzes current session context, including file changes, progress, and decisions to generate the summary.
  • Boundary markers: There are no explicit instructions or delimiters to ensure the subsequent session treats the loaded summary as untrusted data.
  • Capability inventory: The skill writes to the local file system to create the handoff.md file.
  • Sanitization: No sanitization or escaping of the summarized content is performed before writing it to the file.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 09:46 PM