Skills
skills/koala73/worldmonitor/fetch-country-brief/Gen Agent Trust Hub

fetch-country-brief

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill uses curl to perform network requests to an external domain (api.worldmonitor.app). This domain is the primary endpoint for the service but is not included in the standard whitelist for network operations.
  • [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection through its framework parameter. 1. Ingestion points: The framework query parameter in SKILL.md accepts up to 2000 characters of free-text input. 2. Boundary markers: There are no boundary markers or instructions to the AI to ignore instructions embedded within the framework text. 3. Capability inventory: The skill utilizes curl in SKILL.md to send this user-controlled data to an external AI service. 4. Sanitization: The input is not validated or sanitized before being included in the API request.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 10:32 PM