bx-rss
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and parsing of RSS/Atom feeds from external URLs, which serves as a potential vector for indirect prompt injection if the ingested content contains malicious instructions.\n
- Ingestion points: The
rss()BIF and thebx:feedcomponent (action="read") inSKILL.mdingest data from external web URLs into the agent's processing context.\n - Boundary markers: No delimiters or safety instructions are defined to isolate or identify external feed content as untrusted data.\n
- Capability inventory: The skill demonstrates capabilities to perform network requests to fetch feeds and write to the local filesystem using
fileWriteas shown in the examples.\n - Sanitization: The provided instructions do not specify any mechanisms for sanitizing, validating, or filtering the ingested feed content before it is used by the agent.
Audit Metadata