aws-sqs

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes various system commands using the aws CLI and jq to manage SQS queues and messages.
  • [PROMPT_INJECTION]: Potential for indirect prompt injection from external data processed by the agent.
  • Ingestion points: Data is ingested from SQS message bodies via the receive-message command in SKILL.md.
  • Boundary markers: No boundary markers or instructions to ignore embedded commands are present in the scripts.
  • Capability inventory: The skill can execute aws CLI commands and perform message deletions or queue purges.
  • Sanitization: No sanitization is performed on the message bodies before they are presented to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 05:13 AM