The Agent Skills Directory

[SAFE]: The skill is designed for information gathering and synthesis. It follows best practices for technical research, such as mandatory cross-verification of claims, citation of sources, and awareness of version recency. No suspicious patterns such as obfuscation, credential exfiltration, or unauthorized command execution were detected.
[EXTERNAL_DOWNLOADS]: The skill uses WebSearch and WebFetch to retrieve information from external websites. This is a core functionality required for research and is not used to exfiltrate sensitive data or download malicious executables.
[PROMPT_INJECTION]: The skill has an inherent surface for indirect prompt injection because it processes content from external websites.
Ingestion points: Content retrieved from the web via the WebFetch tool.
Boundary markers: None explicitly defined to isolate untrusted content from the agent's internal instructions.
Capability inventory: The skill can write files to the research/ directory and initiate sub-agent tasks via the Agent tool.
Sanitization: No explicit sanitization or filtering of external content is performed before it is processed by the agent.

deep-research