文献自动解析
Analysis
The skill’s summarization purpose is simple, but its code makes it activate on every message and force all user input into a literature-summary format.
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.
用户发送的任何文本,都视为需要解析的文献内容。 ... 不要解释、不要提问 ... trigger: { type: 'always' }The code combines an always-on trigger with instructions to reinterpret every user message as literature content and suppress normal clarification or explanation.
trigger: { type: 'always', // 设为始终触发,即默认技能 }The code says the skill is always triggered as a default skill, while the registry metadata presents the skill as not always-on; this under-discloses its activation behavior.
