The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were detected. The skill defines a legitimate framework for research project management and agent coordination.
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it processes and reflects upon outputs generated by other dispatched agents. This is a design characteristic of recursive agent workflows.
Ingestion points: Agent responses and output files in literature/, proposal/, experiments/, and manuscript/ directories (SKILL.md).
Boundary markers: Not specified.
Capability inventory: dispatch_agent for task execution and local file writing (SKILL.md).
Sanitization: No explicit content sanitization or validation logic is defined within the skill instructions.

research-workflow