Vague Triggers
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The README defines very broad activation examples such as generic requests about commit messages, PR descriptions, changelogs, and impact analysis. In an agentic environment, overly broad trigger phrases can cause the skill to activate during ordinary conversation or on unrelated repository content, increasing the chance that sensitive diffs, internal text, or user intent are processed unexpectedly.
- Content
