database-schema-design
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection because it instructs the agent to ingest and process external, untrusted data artifacts.
- Ingestion points: In SKILL.md, Step 2 directs the agent to pull 'current schema, models, or representative records' into the context.
- Boundary markers: The instructions lack explicit delimiters or warnings to ignore embedded instructions within the ingested data.
- Capability inventory: The skill allows access to powerful tools including 'Bash', 'Write', 'Edit', and 'Read', which increases the impact of potential exploitation.
- Sanitization: There are no defined processes for sanitizing or validating the content of the external files before the agent processes them.
Audit Metadata