The Agent Skills Directory

[SAFE]: The skill utilizes vendor-specific tools (sandbase_call_tool, sandbase_describe_tool) to interface with the Exa research API. These tools are consistent with the stated purpose of deep web research and do not exhibit unauthorized behavior.
[SAFE]: The skill processes external data retrieved via exa_search and exa_contents. While this constitutes an indirect prompt injection surface, the risk is mitigated by the skill's narrow scope and lack of dangerous capabilities such as file system writes or arbitrary shell execution.
[SAFE]: No instances of obfuscation, hardcoded credentials, persistence mechanisms, or privilege escalation patterns were found in the provided files.

exa-deep-search