The Agent Skills Directory

[SAFE]: The skill does not contain any malicious patterns or security risks. It operates as a structured instructional guide for an AI agent to perform conference research and scoring.\n- [PROMPT_INJECTION]: No evidence of prompt injection or instructions to bypass safety guidelines was found. The instructions focus on maintaining a specific analytical framework and do not attempt to manipulate the agent's core safety boundaries.\n- [DATA_EXFILTRATION]: The skill requests client-specific information (ICP, website, etc.) to perform its task, which is consistent with its stated purpose. There are no patterns suggesting unauthorized data exfiltration, credential harvesting, or access to sensitive local files.\n- [REMOTE_CODE_EXECUTION]: There are no commands or instructions that involve downloading or executing external code, scripts, or binary files. The workflow relies entirely on native text processing and standard web search capabilities.

conference-recommendation