seed-data-generator
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill functions by reading and analyzing database schemas to generate data. This process creates an attack surface where malicious instructions embedded within schema metadata, such as table comments or column descriptions, could influence the agent's behavior.
- Ingestion points: The skill reads schema definitions and foreign key relationships (SKILL.md).
- Boundary markers: There are no explicit delimiters or "ignore embedded instructions" warnings defined for the ingestion of schema data.
- Capability inventory: The skill is capable of writing files to the
docs/database-report/directory. - Sanitization: The instructions do not specify any sanitization or validation of the ingested schema content before it is processed by the agent.
Audit Metadata