anfra-validate-aql
Pass
Audited by Gen Agent Trust Hub on Nov 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the
anfraCLI tool for query validation. - [INDIRECT_PROMPT_INJECTION]: The skill processes external AQL query data by interpolating it directly into a shell command string.
- Ingestion points: Untrusted data enters the execution context through the
<query>placeholder or via file input redirected throughcat. - Boundary markers: The example command uses single quotes (
'<query>') to wrap the input, which is a common but bypassable method of preventing shell injection. - Capability inventory: The skill utilizes shell execution capabilities to run the
anfrabinary. - Sanitization: The instructions do not specify any sanitization, escaping, or validation steps for the AQL content before it is passed to the shell.
Audit Metadata