database-seeding
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFECREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The Python code example in SKILL.md contains hardcoded database credentials (
dev_useranddev_password) for a local PostgreSQL database instance. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) when analyzing external database schemas to generate code. Malicious instructions embedded in schema metadata could influence the agent's behavior during the generation process.
- Ingestion points: Database schema analysis (SKILL.md, Workflow Step 1).
- Boundary markers: No delimiters or instructions to ignore embedded content are provided.
- Capability inventory: The skill can generate and execute Python/SQL code and perform database operations (SKILL.md, Example 1 and Supported Technologies).
- Sanitization: No explicit sanitization of schema metadata is mentioned in the instructions.
Audit Metadata