typeql
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were identified in the skill content.
- [COMMAND_EXECUTION]: Documentation includes examples of CLI usage for the
typedb consoleutility. These are informational and facilitate manual database interaction. - [PROMPT_INJECTION]: The skill provides templates for TypeQL queries, creating a surface for indirect prompt injection if user data is used by an agent to generate queries without sanitization.
- Ingestion points: Agent context where user intent or untrusted input is interpolated into TypeQL query strings.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are included in the reference material.
- Capability inventory: Includes destructive operations such as
deleteandundefine, and data retrieval operations viafetch. - Sanitization: No sanitization or input validation guidance is provided within the documentation.
Audit Metadata