Reads recently edited pages from the notion MCP server (read-only) and writes what it found into a Markdown digest in this repo, then opens a pull request with that change. Runs unattended: it asks no questions and makes no writes to notion.
90%
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 reads recently edited pages from a Notion workspace via an MCP server, which can contain user-submitted content.
drew-tessl/repo-schedules-test
82bbe83
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.