pyspark-transformer
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied requests regarding PySpark transformations and data pipelines. It utilizes powerful tools including broad Bash command execution and file system operations, creating a potential injection surface.
- Ingestion points: User prompts and requests regarding PySpark patterns and data transformations (SKILL.md).
- Boundary markers: Absent; no explicit delimiters or instructions to ignore embedded content are defined.
- Capability inventory: Arbitrary shell command execution via
Bash(cmd:*)and full filesystem access viaRead,Write, andEdittools (SKILL.md). - Sanitization: Absent; no specific sanitization, escaping, or validation logic for external content is defined within the skill instructions.
Audit Metadata