zarr-python

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the installation of zarr, s3fs, and gcsfs packages from the official Python Package Index (PyPI). It also documents standard interaction with AWS S3 and Google Cloud Storage (GCS) for remote data access, which is the primary intended functionality of the library.- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from Zarr stores located on local disks or cloud storage. This represents an inherent vulnerability surface where untrusted data could potentially contain instructions intended to influence the agent's behavior if processed without sanitization.
  • Ingestion points: Array reading functions such as zarr.open_array, zarr.open_consolidated, and integration points for Dask and Xarray in SKILL.md and references/api_reference.md.
  • Boundary markers: Code examples do not demonstrate the use of delimiters or specific warnings to ignore instructions embedded within the array data.
  • Capability inventory: The skill has access to file system operations (Read/Write/Edit), network operations via storage backends, and command execution through the Bash tool.
  • Sanitization: There is no documentation regarding the sanitization or validation of data retrieved from the arrays before it is passed to the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 02:35 PM