The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external academic research and reviewer feedback, which serves as a potential surface for indirect prompt injection attacks if the ingested data contains malicious instructions.
Ingestion points: Research drafts, paper content, and user-provided reviewer responses managed in stages 3 through 6.
Boundary markers: The orchestration logic does not define explicit delimiters or instructions for the agent to ignore embedded commands within the processed academic materials.
Capability inventory: The skill dispatches tasks to deep-research, academic-paper, and academic-paper-reviewer skills.
Sanitization: There is no evidence of automated sanitization or filtering of input data within this orchestration layer.
[NO_CODE]: The skill contains only instructional logic and process definitions; it does not include any executable scripts, binary files, or direct system command invocations.

academic-pipeline