The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use curl for fetching data from academic APIs and python3 -c for parsing and formatting JSON results. These operations are restricted to processing legitimate publication metadata.
[EXTERNAL_DOWNLOADS]: Queries external APIs at api.semanticscholar.org and api.openalex.org to retrieve scientific metadata. These are well-known academic services and the queries are consistent with the skill's stated purpose.
[PROMPT_INJECTION]: The skill processes untrusted metadata (titles and abstracts) from external sources, which presents a surface for indirect prompt injection. • Ingestion points: Publication metadata retrieved from Semantic Scholar and OpenAlex APIs. • Boundary markers: None. • Capability inventory: Shell execution via curl and python3 as defined in SKILL.md. • Sanitization: None; external content is printed directly to the conversation context.

literature-search