Orchestrate a comprehensive git workflow from code review through PR creation, leveraging specialized agents for quality assurance, testing, and deployment readiness. This workflow implements modern g
64%
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/git-pr-workflows-git-workflow/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 generic git/PR workflow, but it hardcodes a specific third-party repository (BigSimmo/Communication) as the merge target and sets up auto-merge, which acts on the user's repositories in ways they may not expect. There is no clear malicious intent, so this is medium risk rather than critical.
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 can enable auto-merge and merge PRs into the shared repository (operational repo automation changes), but no irreversible operational loss is evidenced, since the only rollback path is a non-destructive `git revert`, so the tier stays at low.
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 pre-push step at SKILL.md:101 asks the agent to "ensure all review comments addressed," which means reading GitHub PR review comments that outside contributors can post on the repository without the agent selecting a specific item.
BigSimmo/Communication
b4de79a
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.