Security audit
Security checks for vulnerabilities and agentic risk
This is a study-planning helper that runs a small local schedule calculator and does not request sensitive access, persistence, or network activity.
Installers should expect a bilingual study-planning skill that may produce Chinese phase names or templates unless the agent adapts the output. It appears proportionate for learning-plan generation and does not show hidden network access, persistence, credential handling, or destructive actions.
The manifest description says the skill is for "any subject or skill" and lists broad trigger phrases such as "study plan", "learning schedule", "how to learn X", and "prepare for exam". These phrases are common user utterances and the file does not provide exclusion conditions or clearer activation boundaries, increasing the chance of unintended invocation.
Subtle instructions detected that may alter agent decision-making or introduce hidden biases.
## Key Principles
- **Active > Passive**: Always recommend practice over reading
- **Small wins**: Break goals into daily achievable chunks
- **Energy matching**: Hard tasks in peak hours, review in low hours
- **Flexibility**: Plans must bend — include buffer days (10-15% of total)
The generated schedule hard-codes Chinese natural-language labels for all study phases, which imposes a specific language on users regardless of their preferences. This is a natural-language policy concern because the file provides no opt-in, fallback, or explanation that the skill is intended only for Chinese-speaking users.
This markdown file presents all instructional content in Chinese and does not indicate that the user can choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale restriction is clearly documented and justified.
No suspicious patterns detected.