flight-tracker
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The documentation provides shell commands using
curlandjqto interact directly with the OpenSky Network API. These are standard development tools and the usage described is benign for the stated purpose.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests and displays data from external flight tracking services, creating a potential vector for indirect instructions.\n - Ingestion points: Data enters through the
scripts/track.pyandscripts/schedule.pyscripts which queryhttps://opensky-network.organdhttp://api.aviationstack.comrespectively.\n - Boundary markers: The output format does not include explicit boundary markers or warnings to the agent to ignore instructions embedded in the flight data fields (e.g., callsigns, airline names).\n
- Capability inventory: The skill scripts are limited to network GET requests and terminal output; no file system writes or dangerous subprocess execution capabilities were identified.\n
- Sanitization: The scripts parse JSON data but do not perform sanitization or filtering of text fields for prompt injection patterns before displaying them.
Audit Metadata