validate-aql

Pass

Audited by Gen Agent Trust Hub on Oct 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions incorporate the use of the anfra command-line utility, a tool associated with the vendor, to perform AQL query validation via shell execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides a template for executing shell commands using external data, which introduces a surface for indirect prompt injection.
  • Ingestion points: The <query> placeholder and the query.aql file are used to supply external data to the command (SKILL.md).
  • Boundary markers: The instructions use single quotes '<query>' to encapsulate the user-supplied data in the command line.
  • Capability inventory: The skill performs shell execution of the anfra query validate command (SKILL.md).
  • Sanitization: There is no explicit logic described for sanitizing or escaping the query content before it is processed by the shell.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 13, 2026, 07:17 AM