Vague Triggers
Medium
- Confidence
- 93% confidence
- Finding
- The skill declares very broad trigger terms such as 'philosophy', 'ethics', 'philosopher', and even activation when a user says they just installed the skill or do not know how to start. This can cause unintended invocation in unrelated conversations, leading to context hijacking, user confusion, or the skill overriding a more appropriate agent response, though it does not directly enable code execution or data exfiltration.
