Skills
Navigate
skills/xiaolai/ai-research-skills/ray-data/Gen Agent Trust Hub

ray-data

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill demonstrates processing data from external sources such as Amazon S3 and Google Cloud Storage, creating an attack surface for indirect prompt injection. If ingested data contains malicious instructions, it could theoretically attempt to influence the agent's behavior during subsequent processing steps.\n
  • Ingestion points: ray.data.read_parquet, ray.data.read_csv, ray.data.read_json, and ray.data.read_images in SKILL.md.\n
  • Boundary markers: No specific delimitation or 'ignore instructions' warnings are present in the provided templates.\n
  • Capability inventory: The skill utilizes map_batches and map for code execution on data blocks and write_parquet/write_csv for persistent storage across SKILL.md and references/transformations.md.\n
  • Sanitization: The transformation examples do not include explicit input sanitization or schema validation routines.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 03:22 PM