The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill documentation encourages the installation of the 'academic-research-skills' suite from an external GitHub repository (Imbad0202/academic-research-skills) and the use of the 'jeo-skills' toolset.
[DATA_EXFILTRATION]: The skill includes an optional 'Cross-Model Verification' feature (Stage 7) that transmits research data to external AI service providers such as OpenAI, DeepSeek, or other user-specified endpoints for verification purposes.
[COMMAND_EXECUTION]: The skill relies on the Bash tool to orchestrate its multi-stage pipeline, including managing local file state (e.g., Material Passport JSON files) and coordinating various agent tasks.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function involves ingesting and processing untrusted data from the web (via WebFetch) and user-provided academic papers, which serves as a potential surface for indirect prompt injection.
Ingestion points: Research papers fetched from the web in Stage 2 (Literature Sweep) and documents provided by the user for review or revision modes.
Boundary markers: The instructions do not specify explicit delimiters or isolation protocols for the ingested content.
Capability inventory: The skill utilizes Bash, Write, Edit, and WebFetch tools to execute its pipeline stages.
Sanitization: There is no explicit documentation of sanitization or filtering steps for the ingested external research content.

academic-research