Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward DLQ troubleshooting guide, but users should treat its replay command as a real production-changing action.
Install only if you are comfortable letting the agent inspect queue messages, which may contain sensitive data. Before using replay guidance, confirm the root cause is fixed, consumers are idempotent, and the target queue/rate are correct.
The 'Use when' line includes phrases like 'why are messages failing' and 'message processing failures', which are broad enough to overlap with general debugging requests outside a DLQ-specific context. The description does not provide negative examples or explicit boundaries for when the skill should not activate, increasing the risk of unintended invocation.
The manifest description is framed as analysis of dead letter queues: identifying failure patterns, root causes, and remediation strategies. However, the replay command includes an SQS start-message-move-task operation that actively changes queue state by moving messages, which goes beyond analysis into operational modification.
The replay guidance provides commands to move messages from a DLQ back to a live queue without prominent warnings about duplicate processing, replay storms, poison-message loops, or downstream side effects. In operational environments, an unsafe replay can trigger data corruption, repeated failures, service overload, or unintended business actions if messages are not idempotent and prevalidated.
No suspicious patterns detected.
