The Agent Skills Directory

[SAFE]: The skill is a specialized text analysis assistant designed for manuscript diagnostics based on established psychological theories (e.g., Social Identity, Framing Theory). It does not contain any functional code or system-level instructions.
[PROMPT_INJECTION]: No instructions were found that attempt to bypass AI safety guidelines or override system behavior. The instructions are strictly focused on the diagnostic workflow.
[DATA_EXFILTRATION]: There are no network requests, API calls, or commands that access sensitive files or environment variables. All data processing is local to the text provided in the prompt.
[REMOTE_CODE_EXECUTION]: The skill does not download, install, or execute any external scripts or packages. It relies entirely on the underlying LLM's reasoning capabilities.
[OBFUSCATION]: No encoded strings (Base64, Hex), hidden Unicode characters, or homoglyph attacks were detected. The content consists of plain text instructions in Chinese and English, including standard academic DOI references.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to ingest and process user manuscripts, it lacks any executable capabilities (such as shell access, file writing, or network transmission) that could be exploited by malicious content within the analyzed text. The risk is negligible as the output is restricted to text-based suggestions.

dbs-resonate