bel-crm-sql-rules

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a reference guide for SQL query patterns. It documents the limitations of the PostgreSQL tools (such as the lack of support for RETURNING or ON CONFLICT clauses) and provides corrected examples.
  • [INDIRECT_PROMPT_INJECTION]: As a documentation skill that guides how data is retrieved from a database, it technically participates in the data ingestion pipeline. However, it does not introduce new vulnerabilities or bypass existing safety controls.
  • Ingestion points: Guidelines provided in SKILL.md for constructing queries.
  • Boundary markers: None present in the documentation text.
  • Capability inventory: References tool calls to read_query and write_query for database interaction.
  • Sanitization: Not applicable to this static documentation file.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 07:37 PM