The Agent Skills Directory

[SAFE]: The skill uses tools for internet search and PDF generation from the author and trusted providers to fulfill its research purpose.
[SAFE]: No malicious patterns, such as hardcoded credentials, data exfiltration, or unauthorized shell commands, were identified.
[SAFE]: The skill interacts with external data from the internet which constitutes a surface for indirect prompt injection. Ingestion points: Data entering the context from rebyteai/internet-search and rebyteai/deep-research tool outputs. Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between its instructions and the data retrieved. Capability inventory: Use of search and PDF tools; the skill lacks capabilities for direct file system writes or arbitrary code execution. Sanitization: No explicit validation or sanitization of search results is mentioned.

research-workflow