flights
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No evidence of malicious code, obfuscation, or unauthorized access was detected within the skill documentation.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes data from external aviation APIs. This is a standard risk for skills that ingest external data.
- Ingestion points: Flight data responses from FlightAware and AviationStack APIs.
- Boundary markers: Not explicitly defined in the provided markdown file.
- Capability inventory: Restricted to the execution of the local script 'scripts/flights.py'.
- Sanitization: Processing logic is contained in the external script file which was not provided for analysis.
Audit Metadata