The Agent Skills Directory

[SAFE]: The skill contains no executable code or scripts, relying instead on natural language instructions for research workflows. No sensitive data access or network exfiltration patterns were identified.- [PROMPT_INJECTION]: The skill's primary function is to ingest data from external primary sources such as documentation and source code. This creates a surface for indirect prompt injection where malicious content in those sources could potentially influence the agent. However, the instructions mandate citation of sources and the distinction between facts and inferences, which serves as a mitigation.

tracer-research