skills/eho/agent-skills/handoff/Gen Agent Trust Hub

handoff

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements security best practices by requiring the agent to redact sensitive information (API keys, passwords, PII) before generating the handoff document.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it summarizes untrusted conversation history to provide suggestions to a subsequent agent. This is a low-risk finding inherent to the skill's primary function of conversation summarization.
  • Ingestion points: Current conversation history and user-provided arguments in SKILL.md.
  • Boundary markers: The prompt instructions do not specify explicit delimiters or isolation markers for the handoff content within the final user-facing prompt.
  • Capability inventory: File system write (saving the summary to the OS temporary directory).
  • Sanitization: The instructions include a specific directive to redact sensitive credentials and personally identifiable information (PII).
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 01:25 AM
Security Audit — agent-trust-hub — handoff