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

handoff

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes conversation history which acts as a surface for indirect prompt injection. 1. Ingestion points: current conversation history. 2. Boundary markers: absent for the summary document content. 3. Capability inventory: file write access to the user's OS temporary directory. 4. Sanitization: instructions explicitly mandate redacting API keys, passwords, and PII before saving.
  • [SAFE]: The skill includes security best practices by instructing the agent to redact sensitive information before saving the summary and uses the system's temporary directory for transient data storage.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 12:39 AM
Security Audit — agent-trust-hub — handoff