Release a new Remotion version
75%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./.agents/skills/release/SKILL.mdDetected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The skill is a documented Remotion release procedure, but it creates a read-write npm token with `--bypass-2fa` and leaves it unrevoked for up to 7 days, which weakens the user's 2FA protection beyond what the publish task needs.
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
The skill directs the agent to create a long-lived npm token with `--bypass-2fa`, store it in scratchpad files, retrieve passwords and OTPs from 1Password, and log into gcloud and AWS, which are security-sensitive actions that go beyond routine project work, though it involves no sudo, system file, user account, or service configuration changes.
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 changelog step runs `gh pr view` on PRs from the release's merge commits and feeds their outsider-authored titles and author logins into the generated release notes, which is GitHub PR reading and therefore medium.
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.