The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from arbitrary external URLs and search results, which can contain hidden instructions targeting the AI agent.
Ingestion points: The readUrl and search functions in scripts/reader.ts fetch content from external sources.
Boundary markers: There are no specific delimiters or instructions to ignore embedded commands present in the scripts.
Capability inventory: The skill possesses network access via fetch and read access to its own configuration files.
Sanitization: External content is returned as-is without validation, filtering, or sanitization.
[EXTERNAL_DOWNLOADS]: The skill fetches data from Jina AI's official reader and search API endpoints to perform its core functions.

jina-reader