portfolio

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFE
Full Analysis
  • Structured Data Ingestion: The skill processes external data, such as spreadsheets or dockets, to populate its portfolio register. While this introduces a potential surface for indirect prompt injection if malicious instructions were embedded in asset descriptions, the skill mitigates this by using a structured YAML format for the register and requiring explicit user confirmation before recording consequential actions.
  • Human-in-the-Loop Safeguards: A 'consequential-action gate' is implemented for non-legal users, requiring them to verify information with a licensed professional before marking filings as complete. This reduces the risk of automated systems making critical errors or proceeding based on potentially inaccurate input.
  • Scoped File Access: The skill reads and writes to a specific configuration directory (~/.claude/plugins/config/claude-for-legal/ip-legal/). This is a legitimate use of local storage for maintaining its state and register, and does not involve accessing sensitive system directories or user credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 09:46 PM
Security Audit — agent-trust-hub — portfolio