eia-data

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill interacts with the official and well-known US Energy Information Administration (EIA) API at https://api.eia.gov/v2/. All network traffic is directed to this government domain.
  • [COMMAND_EXECUTION]: The skill includes instructions and code examples to retrieve API credentials from ~/.config/eia/credentials using shell commands (grep, cut) and file system modules in Go and Python. This behavior is restricted to the skill's own configuration path and is necessary for its primary function.
  • [PROMPT_INJECTION]: The skill ingests data from the EIA API, which presents a surface for indirect prompt injection. However, the risk is negligible as the data source is a verified government provider of structured numerical statistics.
  • Ingestion points: API responses from https://api.eia.gov/v2/ (referenced in SKILL.md).
  • Boundary markers: No explicit delimiters are used for the interpolation of API data into the agent's output.
  • Capability inventory: The skill uses bash_tool (curl, grep) and Python (requests) to perform network and file operations.
  • Sanitization: The skill does not implement additional sanitization or filtering of the structured JSON data before presentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 06:30 PM