db-tool
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes database operations using the
bun db-toolcommand, which is a wrapper for the author's toolkit.\n- [PROMPT_INJECTION]: The skill has an indirect injection surface because it processes database records which are untrusted external data.\n - Ingestion points: Results from SQL queries in
SKILL.md.\n - Boundary markers: None specified.\n
- Capability inventory: Subprocess execution for database queries in
SKILL.md.\n - Sanitization: Not implemented in the skill instructions.\n- [SAFE]: Database credentials are managed via environment variables rather than hardcoded secrets, which is a standard security practice.
Audit Metadata