Vague Triggers
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill enables allow_implicit_invocation without any visible trigger constraints in this file, which can cause the skill to activate in broader conversational contexts than intended. Because the skill reads attacker-influenced URLs or domains to fetch and interpret robots.txt, overly broad automatic invocation increases the chance of untrusted prompt context steering the agent into unintended external access or misleading security conclusions.
- Content
