小沐宝咖啡
Analysis
This instruction-only coffee-stall helper looks purpose-aligned, but guardians should review the child-voice persona and schedule/location content before using it publicly.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
AI 能以**7岁小女孩的口吻**自动回答
The skill intentionally makes the agent answer in a 7-year-old first-person brand persona. This is disclosed and purpose-aligned, but users should understand the responses are AI-generated and not direct commitments from the real child.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
| 4月19日(周六) | 六 | 15:00 - 18:00 | 小区北门广场 | ✅ 已确认 |
The packaged reference context includes time and location details for a stall described as run by a 7-year-old. Returning this schedule is part of the skill's purpose, but minor-related location information should be shared deliberately.
