Fetch container image labels, validate registry ownership, resolve tag/digest via SBOM, and report the SBOM artifact reference for a Red Hat container image.
82%
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 inspects container image metadata and downloads SBOM documents from registries where an outsider-published image or package could contain embedded untrusted text.
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.