Create, edit, or comment on Remotion GitHub issues.
82%
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 interacts with GitHub issues (creating, editing, and viewing them), but the prompt ingestion rules explicitly consider ANY GitHub issue/PR reading as a medium risk because outsiders can submit free text into issues.
remotion-dev/remotion
cc7879e
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.