Vague Triggers
Medium
- Confidence
- 81% confidence
- Finding
- The skill description uses broad triggers such as summarizing, digesting, extracting key points from a URL or web page, and batch comparison tasks, which can cause over-selection for common user requests. In an agent environment, this increases the chance the skill is invoked on untrusted or sensitive URLs without sufficient scope checks, potentially enabling unintended network access or processing of attacker-controlled content.