oebb-scotty

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection surface. • Ingestion points: The scripts arrivals.sh, departures.sh, search-station.sh, and trip.sh accept station names, dates, and times as CLI arguments. • Boundary markers: No delimiters or instructions are used to separate user-provided data from the API request structure. • Capability inventory: The skill performs network requests to the official ÖBB domain via curl and processes responses with jq. • Sanitization: Absent; user input is directly interpolated into JSON payloads within the shell scripts.
  • [COMMAND_EXECUTION]: The skill utilizes local shell scripts to perform network requests and data processing. • Evidence: The skill includes five scripts (arrivals.sh, departures.sh, disruptions.sh, search-station.sh, trip.sh) that execute curl and jq commands to fetch and filter data from the ÖBB Scotty API. This behavior is expected for the skill's purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 02:43 AM