Vague Triggers
Medium
- Confidence
- 90% confidence
- Finding
- The skill advertises broad trigger phrases like "Analyze my CDK app for security issues" and "Review the IAM policies in my CDK stacks" without clear scoping or activation boundaries. In an agent environment, such generic requests can overlap with normal conversation and cause the skill to activate unexpectedly, leading to unintended repository inspection, command suggestions, or handling of sensitive infrastructure context.
