serenereader
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and process external data from RSS feeds via the SereneReader API, which introduces a potential surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the agent context through the
title,snippet, andauthorfields returned by the/api/v1/articlesendpoint as documented inSKILL.md. - Boundary markers: The provided instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when the agent handles content from RSS feeds.
- Capability inventory: The agent is granted network access to
serenereader.comand is instructed to perform text-based tasks like summarization and grouping on the external data. - Sanitization: There are no requirements for the agent to sanitize or validate the integrity of the RSS feed content before processing it.
Audit Metadata