The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests academic metadata such as paper titles, author names, and abstracts from the well-known CNKI service. While this represents a data ingestion surface, the risk is assessed as safe because the data originates from a reputable academic repository and is processed by a static Python analysis script for statistical purposes rather than being used to drive the agent's decision-making logic.\n- [COMMAND_EXECUTION]: The skill executes a local Python script provided within the skill package to perform data analysis and generate reports. This is a legitimate functional requirement of the skill and involves standard operations like creating directories and writing a Word document to the user's Downloads folder using well-known libraries.\n- [SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration attempts were found. The skill adheres to its stated purpose of providing macro-level analysis of academic journals.

cjournal-analyzer