The Agent Skills Directory

[SAFE]: The skill instructions are focused exclusively on academic paper analysis and follow a structured, benign workflow including summarization, consistency checks, and critical evaluation.
[PROMPT_INJECTION]: The skill features a surface for indirect prompt injection because it processes untrusted research papers provided by users. However, this is inherent to its primary purpose and the instructions do not contain any malicious triggers.
Ingestion points: Processes PDF documents, LaTeX source files, and plain text paper content (SKILL.md).
Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between paper content and its own instructional logic.
Capability inventory: The skill uses file-reading tools like Read, Grep, and Glob to analyze paper contents (SKILL.md).
Sanitization: No explicit sanitization or filtering of external paper content is defined before processing.
[SAFE]: Installation commands in the README use npx to fetch the skill from the official repository of the authoring vendor (BESSER-PEARL), which is expected behavior for this platform.

research-paper-review