Security audit
Security checks for vulnerabilities and agentic risk
This skill does what it says: it turns a user-provided link into Feishu source and analysis documents, with normal privacy considerations for uploading content to Feishu.
Install this only if you are comfortable with the agent fetching the link you provide and writing the full captured text plus source metadata into Feishu. Avoid using it on confidential, internal, paywalled, personal, or regulated content unless your Feishu workspace is approved for storing that material.
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
# clawbox
OpenClaw skill: turn a shared web link into two Feishu docs (source archive + analysis summary).
The skill directs the agent to fetch arbitrary external URLs and then create or update Feishu documents containing the captured content and source metadata, but it does not require notifying the user that article contents, URLs, titles, and capture timestamps will be transmitted to a third-party platform. This creates a privacy and data-handling risk, especially if users provide internal, paywalled, sensitive, or personal links under the assumption the task is only local or ephemeral.
The template headings and instructions are entirely in Chinese, which implicitly requires responses in a specific language. The policy forbids forcing a language or locale unless the user is given a choice or the constraint is clearly justified.