skills/tylergannon/agents/handoff/Gen Agent Trust Hub

handoff

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary purpose is conversation management and handoff. It includes explicit instructions to redact secrets and PII (Personally Identifiable Information), which aligns with security best practices for handling session data.
  • [DATA_EXFILTRATION]: The skill instructs the agent to save the handoff document to the operating system's temporary directory rather than the local workspace. While this involves file system operations outside the immediate project scope, it is a standard practice for temporary session artifacts and the risk is mitigated by the explicit instruction to redact all sensitive information first.
  • [PROMPT_INJECTION]: Because the skill involves summarizing conversation history, it is subject to the risk of indirect prompt injection where malicious instructions within the dialogue could be summarized and passed to a future agent. This is a common property of summarization tasks and the skill attempts to mitigate credential leakage through redaction instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 10:19 PM