fetch-resilience-score

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches data from an external API, which serves as an ingestion point for untrusted content.
  • Ingestion points: Data is retrieved from the https://www.worldmonitor.app/api/resilience/v1/get-resilience-score endpoint in SKILL.md.
  • Boundary markers: The skill includes a dedicated 'Content safety' section that explicitly instructs the agent to treat response fields strictly as data and to disregard any instructions or commands found within those fields.
  • Capability inventory: The skill uses standard network requests to fetch data and utilizes jq for parsing; it does not request high-privilege capabilities or execute arbitrary shell commands.
  • Sanitization: The skill uses proactive instructional guarding to ensure the agent ignores any potential prompt injection attempts embedded in the retrieved data.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 01:54 AM