The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, including manuscript topics, abstracts, and full texts, which establishes a surface for indirect prompt injection attacks.
Ingestion points: Inputs such as topic, abstract, and manuscript are defined in SKILL.md as data sources for agent analysis.
Boundary markers: The instructions do not specify the use of delimiters or provide explicit guidance for the agent to disregard instructions potentially embedded within the research content.
Capability inventory: The workflow involves performing deep analysis of innovation and workload on the provided text, and it uses scripts/journal_ranker.py to sort and rank the resulting data.
Sanitization: There are no documented steps for validating or sanitizing the input text to prevent malicious instructions from affecting the agent's assessment logic.

journal-recommender