The Agent Skills Directory

[SAFE]: The skill provides documentation for built-in research capabilities. No malicious code, obfuscation, or unauthorized access attempts were detected. The instructions prioritize the use of platform-native tools and explicitly discourage unsafe practices like manual curl commands.
[INDIRECT_PROMPT_INJECTION]: The skill serves as an ingestion point for external data from scientific databases (Scopus, OpenAlex), which constitutes an indirect prompt injection surface.
Ingestion points: Data is brought into the agent's context through the output of the rp_search and rp_abstracts tools, containing titles and abstracts.
Boundary markers: The instructions do not define specific delimiters to wrap the ingested external content.
Capability inventory: The agent has the ability to search, traverse citations, and write full-text results to the workspace via rp_fulltext.
Sanitization: There is no mention of filtering or sanitizing the retrieved bibliographic metadata.
Note: This risk is characteristic of any search-related skill and is considered low-impact in this context.

searching-literature