uav-mission-compute-sdk
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill features an attack surface for indirect prompt injection by processing external data streams.
- Ingestion points: Untrusted data enters the context via RTSP streams and MQTT telemetry as described in SKILL.md.
- Boundary markers: The instructions lack specific delimiters or warnings to ignore instructions embedded in telemetry or stream metadata.
- Capability inventory: The skill uses system tools including docker compose, make, and curl for operations in SKILL.md and evals.json.
- Sanitization: There is no evidence of data sanitization or validation logic for the external telemetry inputs.
- [EXTERNAL_DOWNLOADS]: The skill references documentation and configuration files from the Intel Open Edge Platform Team's official GitHub repository, which is consistent with the skill's stated authorship.
Audit Metadata