The skill directs the agent to unlock previously locked issues without checking why they were locked or obtaining maintainer approval.
- Category
- Excessive Agency
- Confidence
- 97% confidence
- Finding
The skill explicitly tells the agent to unlock a relevant issue whenever it has permission, without checking the lock reason or obtaining authorization to reverse it. A requester could use a support question to induce removal of an intentional moderation restriction, enabling renewed spam, harassment, or unwanted participation; the surrounding safety checks do not establish that unlocking is authorized.
- Content
