natural-language-postgres
Warn
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user or agent to clone a repository from an external source (
https://github.com/Eng0AI/natural-language-postgres.git) and proceed with a full dependency installation viapnpm install. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to translate plain English questions into PostgreSQL queries, creating a pathway for malicious data to influence database operations.
- Ingestion points: Natural language questions provided by the user in a chat interface.
- Boundary markers: The provided documentation lacks specific instructions or system prompts intended to delimit user input or prevent the execution of embedded instructions.
- Capability inventory: The application is designed to query a PostgreSQL database, which may include read or write access depending on the database configuration.
- Sanitization: The setup instructions do not describe any sanitization, validation, or parameterized query mechanisms to mitigate SQL injection or prompt-based manipulation.
Audit Metadata