Discover the RSS/Atom feed URL for a website, then run the fetch-rss.mjs script to retrieve and parse articles from the feed.
72
91%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Yes—when the required workflow runs `rss-reader <feed_url>`, `scripts/fetch-rss.mjs` fetches and parses outsider-authored RSS/Atom XML from the user-supplied `feedUrl` (`parser.parseURL(feedUrl)`), then injects the resulting feed fields (including `item.contentEncoded`/`item.description`/`summary`) as readable markdown into `stdout`, which is passed into the LLM context.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The skill calls parser.parseURL on an arbitrary user-supplied feed URL (e.g., "<feed_url>" / "<url>") at runtime and returns the fetched feed content as markdown intended for the LLM, so remote feed content can directly control prompts.
bcef823
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.