The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to ingest and synthesize untrusted external data from the open web.
Ingestion points: The instructions specify using agent-browser to read full-text articles and retrieve content from external websites (SKILL.md).
Boundary markers: The instructions lack explicit directives for the agent to use delimiters or ignore potential instructions embedded within the retrieved web content.
Capability inventory: The skill utilizes multi-search-engine, pubmed-search, and agent-browser to find, read, and process external information.
Sanitization: There are no instructions for sanitizing or validating external content before it is integrated into the agent's context and final report.

deep-research