handoff

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes the current conversation history to generate a summary. This untrusted data source could contain malicious instructions intended to persist across agent sessions through the handoff document.
  • Ingestion points: Conversation history processed during the handoff generation (SKILL.md).
  • Boundary markers: The prompt does not define clear delimiters for the ingested conversation content.
  • Capability inventory: The skill writes the generated summary to the OS temporary directory (SKILL.md).
  • Sanitization: Includes explicit instructions for the agent to redact sensitive information such as API keys and passwords before saving.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 01:40 PM
Security Audit — agent-trust-hub — handoff