fuel-pricing
Fail
Audited by Snyk on Mar 10, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill explicitly asks users to "share" their FuelCheck API key and secret and provides a shell here-doc that embeds those secrets verbatim into a credentials file, meaning the agent would need to accept and output exact secret values to save/confirm them.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill clearly fetches and ingests open/public community data (e.g., PetrolSpy and FuelSnoop via scripts/fuel_prices.py's fetch_petrolspy and fetch_fuelsnoop and SKILL.md "Data Sources"), and that untrusted third‑party content is parsed and used to choose and present recommended stations, so it can materially influence agent behavior and enable indirect prompt injection.
Audit Metadata