skills/hainrixz/claude-db/explain/Gen Agent Trust Hub

explain

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates as intended for database documentation without performing any network operations or unauthorized data access.
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute local scripts (scripts/detect-stack.mjs, scripts/parse-schema.mjs, parse-orm-python.py, and scripts/gen-diagram.mjs) to parse database models. These scripts are part of the skill package.
  • [PROMPT_INJECTION]: The skill processes untrusted input such as database schema files and SQL query plans, which constitutes an indirect prompt injection surface. 1. Ingestion points: Target files provided via $ARGUMENTS and pasted EXPLAIN plans. 2. Boundary markers: No specific delimiters are used to isolate external content. 3. Capability inventory: Execution of local scripts via Bash and file system read tools (Grep, Glob, Read). 4. Sanitization: No data validation or sanitization process is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 10:02 PM
Security Audit — agent-trust-hub — explain