Ops AI Transform
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its data processing workflow.
- Ingestion points: The skill ingests untrusted data from table columns specified in the source_columns input field as described in SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the prompt templates used for generating column values.
- Capability inventory: The skill utilizes the ai_transform_ops_column action which can write AI-generated content back into the database based on interpolated data.
- Sanitization: The instructions do not define any sanitization, filtering, or validation of the column data before it is processed by the AI.
Audit Metadata