sensor-fusion-engineer
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill guidelines instruct the agent to ingest and analyze external, potentially untrusted data sources.
- Ingestion points: The skill explicitly mentions processing 'rosbag' files, 'logs', and 'simulation datasets' in SKILL.md and throughout the references, specifically in
references/evaluation_simulation_and_metrics.md. - Boundary markers: The instructions do not define protective boundary markers or instructions to ignore potential commands embedded within the data files.
- Capability inventory: The skill is designed for use by agents capable of interacting with engineering datasets and file systems.
- Sanitization: No guidance is provided for sanitizing or validating the contents of ingested external logs or datasets.
Audit Metadata