The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the system date command to generate formatted timestamps for file naming and Org-mode metadata, ensuring proper document organization within the user's environment.
[EXTERNAL_DOWNLOADS]: The skill retrieves academic content from external sources, specifically Arxiv URLs and PDF files, using tools such as WebFetch and the author's internal ljg-fetch utility to obtain data for analysis.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as its core workflow involves ingesting and processing untrusted text from external research papers.
Ingestion points: The skill reads data from Arxiv URLs, PDF files, and web search results to extract abstracts, introductions, and methodology sections.
Boundary markers: There are no explicit instructions or delimiters defined to prevent the LLM from following malicious instructions that might be embedded within the content of the academic papers being analyzed.
Capability inventory: The skill possesses the ability to write files to the local directory ~/Documents/notes/ and execute further network-based search and fetch operations.
Sanitization: No sanitization or validation logic is specified to filter the external content before it is processed through the multi-stage analysis pipeline.

ljg-paper