Vague Triggers
Medium
- Confidence
- 84% confidence
- Finding
- The invocation description is overly broad and can activate the skill on generic TikTok-related mentions, not just clear requests for caption or script generation. This can cause incorrect skill routing, leading an agent to produce inappropriate outputs or bypass a more suitable skill, which is a real security/control-plane issue in agent orchestration even though the content itself is not overtly malicious.
