schema-exploration
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- NO_CODE (SAFE): The skill consists exclusively of Markdown documentation. No scripts (Python, JavaScript, etc.) or configuration files are present.
- DATA_EXPOSURE (SAFE): The instructions detail how to use database exploration tools. No hardcoded credentials, API keys, or sensitive file paths were found.
- PROMPT_INJECTION (SAFE): The Markdown text follows a standard instructional format and does not attempt to bypass AI safety filters or override system prompts.
- INDIRECT_PROMPT_INJECTION (LOW): The skill defines a workflow that ingests external data (database schema and sample data). Mandatory evidence: 1. Ingestion points: Output from sql_db_list_tables and sql_db_schema. 2. Boundary markers: None specified in instructions. 3. Capability inventory: Limited to read-only database exploration. 4. Sanitization: Not explicitly mentioned. This represents a standard surface risk for data-processing skills.
Audit Metadata