skills/will-ness-ai/skills/handoff/Gen Agent Trust Hub

handoff

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is a standard utility for session management, generating handoff summaries to maintain context between agent interactions.
  • [PROMPT_INJECTION]: The skill processes external, untrusted data including conversation history and user arguments, which constitutes an indirect prompt injection surface. The 'suggested skills' section also creates a multi-step chain where the output could influence the next agent's actions. These risks are inherent to the skill's primary purpose and are mitigated by instructions to redact sensitive information.
  • Ingestion points: Conversation history and user arguments (SKILL.md).
  • Boundary markers: No explicit delimiters or boundary instructions are provided for the summarized data.
  • Capability inventory: Writing a summary file to the operating system's temporary directory.
  • Sanitization: Explicit instruction to redact API keys, passwords, and PII.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 04:57 PM
Security Audit — agent-trust-hub — handoff