natural-language-postgres-presentation
Warn
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to download source code from an external repository located at
https://github.com/Eng0AI/natural-language-postgres-presentation.git. - [COMMAND_EXECUTION]: The setup process involves several shell commands including
git clone,pnpm install,pnpm build, andpnpm devwhich execute third-party code on the local system. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the creation of an application that translates natural language into SQL queries, representing an attack surface for indirect prompt injection.
- Ingestion points: User-provided natural language queries processed in
SKILL.md's documented workflow. - Boundary markers: None documented in the instructions or setup.
- Capability inventory: Execution of generated SQL queries against a connected PostgreSQL database.
- Sanitization: The provided documentation does not specify validation or sanitization layers for the natural language inputs before SQL generation.
Audit Metadata