rss-reader
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Node.js script (
fetch-rss.mjs) to retrieve and format RSS feed data. - [EXTERNAL_DOWNLOADS]: The
fetch-rss.mjsscript performs network requests to arbitrary external URLs provided by the user or discovered during the URL discovery step to fetch XML feed content. - [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) because it ingests and processes untrusted content from external RSS feeds.
- Ingestion points: External data enters the system via the
parser.parseURL(feedUrl)call inscripts/fetch-rss.mjs. - Boundary markers: The output is structured with Markdown headers and thematic breaks (
---), providing some separation between the feed content and agent instructions. - Capability inventory: The skill has network-read capabilities (via
rss-parser) and executes a local script, but it does not have file-write or persistence capabilities. - Sanitization: The script performs no sanitization of the article content, summaries, or titles before outputting them to the agent's context.
Audit Metadata