fuel-pricing

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly asks users to "Share those with me" for FuelCheck API Key/Secret and provides a here-doc/bash snippet to write those values into ~/.config/fuel-pricing/credentials.json, which implies the LLM will accept, handle, and embed secret values verbatim (exfiltration risk).

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). This skill's runtime script (scripts/fuel_prices.py) fetches public third‑party data — including community aggregators FuelSnoop (Supabase endpoint in fetch_fuelsnoop) and PetrolSpy (petrolspy.com.au in fetch_petrolspy) as shown in the adapters and the SKILL.md Data Sources — and directly ingests and uses those untrusted/user-contributed results to pick/sort stations and drive recommendations, so external content can materially influence agent actions.