multi-sport-match-research

Pass

Audited by Gen Agent Trust Hub on Oct 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as an ingestion surface for external sports data, which is processed by the agent to fulfill user requests.
  • Ingestion Points: Sports fixtures, statistics, and news summaries fetched via scripts/crawlora.sh from the vendor API at api.crawlora.net.
  • Boundary Markers: Instructions in SKILL.md direct the agent to preserve source identifiers and distinguish between provider snapshots, but no explicit structural delimiters are defined for the fetched data.
  • Capability Inventory: The skill's capabilities are limited to performing network GET requests to the specific vendor API.
  • Sanitization: The included helper script implements best practices, such as URL-encoding all query parameters, using a secure temporary configuration file for the API key to prevent exposure in process lists, and enforcing a strict allow-list of authorized API paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 20, 2026, 06:48 AM