Vague Triggers
Low
- Confidence
- 82% confidence
- Finding
- The skill explicitly instructs the agent to set up a periodic heartbeat and references an external specification, but it does not define safe bounds on frequency, permitted actions, approval requirements, or resource limits. In an agent setting, an open-ended recurring loop that reads and acts on user-generated content can amplify prompt-injection, spam, unintended external actions, and uncontrolled API usage over time.
