Intelligently recommend the optimal S2I builder image or container base image for a project based on detected language/framework, use-case requirements, security posture, and deployment target. Supports GitHub URLs for remote project analysis (delegates to /detect-project). Use this skill when the user needs a container image recommendation, wants to compare image options, or asks about production vs development images. Triggers on /recommend-image command, or when advanced image selection beyond basic version matching is needed. Supports Node.js, Python, Java, Go, Ruby, .NET, PHP, and Perl on Red Hat UBI.
80%
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
Fix and improve this skill with Tessl
tessl review fix ./rh-developer/skills/recommend-image/SKILL.mdThe 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 GitHub URL path delegates to `/detect-project`, which reads files from a user-supplied repository (an arbitrary, selected URL the agent fetches, so it is not forced delivery), while the other inputs are first-party Red Hat registry and Security Data API responses.
RHEcosystemAppEng/agentic-plugins
89ba231
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.