query-budget-enforcer

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by ingesting and processing untrusted SQL queries for analysis.
  • Ingestion points: SQL query strings provided by users or external systems as described in SKILL.md.
  • Boundary markers: The protocol lacks instructions to encapsulate input queries or warn the agent against executing instructions found within the data.
  • Capability inventory: The agent is directed to write analysis results to files in the 'docs/database-report/' directory.
  • Sanitization: No input validation or sanitization of the SQL queries is defined before the data is processed or written to report files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 06:36 AM