sql-queries

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests and processes external data provided by the user to perform its primary function.
  • Ingestion points: The skill reads and analyzes uploaded SQL schema files, documentation, and database diagram descriptions provided by the user in 'Step 1' and 'Example 1'.
  • Boundary markers: There are no instructions or delimiters defined to guide the agent to ignore potential instructions embedded within the ingested data files.
  • Capability inventory: The skill has the capability to generate SQL code and 'executable SQL scripts', which could be leveraged by an attacker to generate malicious queries or data-destructive commands if the agent follows instructions hidden in a schema file.
  • Sanitization: The skill does not implement any validation, sanitization, or filtering of the content within the schema files before processing them.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 01:28 PM
Security Audit — agent-trust-hub — sql-queries