announcement-analysis

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to interact with the finx CLI tool to query the gildata-aidata database for financial indicators, valuation metrics, and institutional ratings. This is a standard and expected functional use of platform-integrated financial tools.
  • [PROMPT_INJECTION]: The skill processes untrusted external data from user-uploaded files and web search results, presenting a surface for indirect prompt injection. This is a functional requirement for the skill's primary purpose of document analysis, and the instructions provide a rigid reporting framework that acts as a natural constraint on agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 06:41 AM
Security Audit — agent-trust-hub — announcement-analysis