Bilingual Learning
PassAudited by ClawScan on May 13, 2026.
Overview
This appears to be a local bilingual-learning helper that changes responses and stores vocabulary lists, with no evidence of credential use, network exfiltration, or hidden execution.
Install this only if you want the agent to add bilingual learning checks to its answers. The reviewed artifacts show local word-list storage and local Python helper commands, but no network access, credential use, or hidden execution. Be aware that vocabulary history is persisted locally and can be cleared by the documented CLI commands.
Findings (4)
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.
When this skill is active, answers may include bilingual wording, vocabulary checks, or quizzes even if the underlying task is not about language learning.
The skill explicitly tells the agent to alter final responses with bilingual learning content. This matches the skill's purpose, but it changes the shape of the user's normal answers when invoked.
在 agent 最终输出前强制双语处理
Use this skill only when you want learning content added to responses, and disable or avoid invoking it for conversations where you want unmodified answers.
The skill keeps a local record of vocabulary-learning state, such as words added to the new-word or known-word libraries.
The code persists vocabulary entries in local JSON word-library files, which can then be reused by later quiz and detection flows.
self.path = DataPath / f"{name}.json" ... self.words.append(entry) ... self.save()Review or clear the local word-list files if you do not want vocabulary history retained, and avoid adding sensitive personal terms as vocabulary entries.
Some documented files or setup expectations may not match the packaged skill, which could cause confusion or non-working commands.
The README references a skill entry script that is not included in the provided file manifest. The artifacts otherwise show simple local Python helpers, so this is a documentation/package completeness note rather than evidence of malicious code.
scripts/skill.py # Skill 主入口
If using the helper scripts, verify the actual files present in the installed package and do not assume undocumented or missing entry points exist.
Running the clear command can erase the saved new-word or known-word list.
The CLI includes a command that clears the local word library. It is scoped to the skill's own vocabulary files and is user-directed, but it can remove saved learning data.
elif cmd == "clear": ... lib.clear() ... print(f"{'生词库' if target == '-n' else '熟词库'} 已清空")Run clear/delete commands only intentionally, and back up word-list files if the saved vocabulary matters to you.