Teaches an agent how to create, publish, version, organize, share, and comment on Centaur Spec reports through the centaurspec MCP server; use when uploading/sharing an HTML report, publishing a new version of one under the same link, organizing reports into folders, controlling who can view/edit a report, or reading/resolving reviewer comments.
88%
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 canonical home for this skill is centaur-spec-reports in agranado2k/ai-report-platform
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 required collaboration workflow has the agent call `reports_list_comments` on a report, and reviewers who are outside the owner's org (via allowlist, public link, or write grants) can post comment text into that thread without the agent selecting a specific comment.
agranado2k/ai-report-platform
caeb0da
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.