generate-release-notes
61%
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 ./.github/skills/generate-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 calls the `getReleaseFeatures` tool from the workspace extension and ingests its returned feature text without the agent selecting a specific item, and if that data is drawn from issue or PR trackers, outsiders can write into it, so under recall-first scoring this is medium.
microsoft/vscode-docs
9dc724b
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.