The Agent Skills Directory

[SAFE]: The skill provides structured guidelines for research, focusing on search strategies, data extraction, and fact-checking. No evidence of prompt injection, data exfiltration, or unauthorized command execution was found.\n- [INDIRECT_PROMPT_INJECTION]: The skill involves ingesting data from external sources during the extraction phase. While this is a standard attack surface for indirect prompt injection, the instructions explicitly advise against dumping full pages into context, which acts as a mitigation. No specific boundary markers or sanitization logic is provided within the instructions, which is expected for high-level guidance.

deep-research