tool-gdelt-news

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill fetches external news content which could theoretically contain instructions meant to influence the agent. 1. Ingestion points: External news headlines from GDELT API. 2. Boundary markers: Not specified in documentation. 3. Capability inventory: No executable scripts are provided in this skill package. 4. Sanitization: Not specified in the interface description.
  • No Code (SAFE): The skill consists entirely of metadata and documentation (SKILL.md) with no accompanying scripts, binaries, or configuration files that could execute logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 06:27 AM