generate-synthetic-data
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the generation of synthetic queries by interpolating user-supplied application descriptions and dimension values into its prompting logic. This creates a vulnerability surface for indirect prompt injection if the user-controlled data is maliciously crafted. * Ingestion points: The prompt templates in Step 3 and Step 4 of SKILL.md ingest variables such as application descriptions and dimension values. * Boundary markers: The prompts lack explicit delimiters or instructions to isolate user-supplied data from the rest of the prompt context. * Capability inventory: The skill leverages the agent's text generation capabilities to produce queries based on these inputs. * Sanitization: There is no mechanism for sanitizing or validating the input strings before they are incorporated into the prompt templates.
Audit Metadata