Explain a CVE using Red Hat's severity rating system. Looks up the CVE, explains the rating, and suggests a course of action.
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
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.
The workflow fetches CVE metadata, advisories, and errata from Red Hat via API or WebFetch based on a specific CVE ID provided by the user, representing active search/fetch of selected URLs rather than unprompted monitoring of an untrusted feed.
RHEcosystemAppEng/agentic-plugins
df1d156
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.