flight-tracker

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions and associated API map contain no evidence of malicious patterns, such as prompt injection, data exfiltration, or unauthorized command execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest flight status data from an external source, which represents a standard surface for indirect prompt injection.
  • Ingestion points: External data returned from the strale_flight_status tool (SKILL.md).
  • Boundary markers: The workflow instructions include steps to synthesize findings and separate observations from interpretations, which helps mitigate accidental obedience to embedded data.
  • Capability inventory: The skill is limited to calling specified tools via the sandbase_call_tool gateway and does not have file-system write or arbitrary shell execution capabilities.
  • Sanitization: Standard instructional sanitization is requested in the workflow (citing sources, noting gaps).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 11:30 PM
Security Audit — agent-trust-hub — flight-tracker