rerun-chunk-processing
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the creation of pipelines that ingest and process various external data formats, which could contain malicious instructions.
- Ingestion points: Data is read via
McapReader,UrdfTree,ParquetReader,Mp4Reader,Hdf5Reader, andRrdReaderas described inSKILL.md. - Boundary markers: The instructions do not specify the use of boundary markers or safety delimiters to isolate external data from the agent's logic.
- Capability inventory: The API enables file writing capabilities via
write_rrdand arbitrary data transformation logic. - Sanitization: There is no guidance provided for sanitizing or validating external content before it is processed or stored.
- [DYNAMIC_EXECUTION]: The skill utilizes functional programming patterns that involve executing logic on data at runtime.
- Evidence: The instructions describe using
Selector.pipe(lambda ...)andstream.map(fn)to apply Python and PyArrow compute functions dynamically within the chunk processing pipeline.
Audit Metadata