Create or update Chatto release pages from Sweet Release state, tags, changelog entries, and PRs.
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 ./.agents/skills/chatto-release-notes/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 required workflow reads commits, PR descriptions, and the Sweet release PR from GitHub (lines 14-15, 21-22), and outsiders can author PR descriptions and commit messages that the agent ingests without selecting a specific item.
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.