High-level review rules for Chatto client and server changes, including API and protobuf changes, permissions, behavior regressions, multi-server compatibility, and multi-replica safety. Use for every review of a Chatto change, branch, or PR, including self-review.
87%
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 required workflow runs on every Chatto PR review, and reviewing a PR means reading its description, comments, and diff, which outside contributors can author, so this is GitHub PR reading and falls under medium.
chattocorp/chatto
da08d92
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.