Finishing a Development Branch

Name: superpowers/finishing-a-development-branch
Author: obra

View on GitHub↗

Share on X Share on LinkedIn Share on Bluesky

40Medium

The skill allows a manipulated agent to inject

ThreatsCI SM CS BC S HITL

Behavior Analysis

Description verified — behavior matches claim

Claims to do

Finishing a Development Branch: Guide completion of development work by presenting clear options and handling chosen workflow.

Actually does

This skill executes various `git` commands to manage branches (merge, delete, push) and worktrees, runs project-specific test commands (`npm test`, `cargo test`, `pytest`, `go test`), and interacts with GitHub via `gh pr create` to create pull requests. It determines the base branch and offers four options for completing development work.

Threat Analysis

AI Agent Traps ↗Scanned 4/16/2026

Content InjectionPerceptionclean

Semantic ManipulationReasoningclean

Cognitive StateMemory & Learningclean

Behavioural ControlActionclean

SystemicMulti-Agent Dynamicsclean

Human-in-the-LoopHuman Overseer1 finding

Skill Info

Nameobra/superpowers/finishing-a-development-branch

Registrygithub

Versionc4bbe651cb1b

PURLpkg:github/obra/superpowers@c4bbe651cb1b?skill=finishing-a-development-branch

Stars180,084

Installs52,400

Source

Repository ↗SKILL.md ↗

SHA-256dd2f82c6dc85...

SHA-1ad48721df9fa...

MD5843f51fc511c...

TLSH0291b4a2ad87...

ssdeep48:kzgsJEjIk...

Size4,250 bytes

Install

This skill has been flagged as potentially malicious. Review the findings below before installing.

GitHub

https://github.com/obra/superpowers

52,400 installs

Claude CodeDocs

/plugin marketplace add obra/superpowers

/plugin install finishing-a-development-branch@obra/superpowers

CodexDocs

Gemini CLIDocs

gemini extensions install https://github.com/obra/superpowers.git --consent

CursorDocs

Skills.shDocs

npx skills add https://github.com/obra/superpowers

Assessments (1)

AI Agent Traps ↗

Agent-generated content for Pull Requestmediumsocial engineering

The skill instructs the agent to create a GitHub Pull Request with a title and body generated by the agent. If the agent is compromised or manipulated, it could inject malicious links, phishing content, or misleading information into the PR description, potentially social engineering human reviewers.

70% confidenceline 70

gh pr create --title "<title>" --body "$(cat <<'EOF' ... EOF)"

Version History (4)

c4bbe651cb1bcurrent40Medium4/16/2026 f9b088f7b3a640Medium4/14/2026 a569527b89c140Medium4/14/2026 917e5f53b16b70High4/14/2026

Badge

Markdown

[![Mondoo Skill Check](https://mondoo.com/ai-agent-security/api/badge/github/obra/superpowers/finishing-a-development-branch.svg)](https://mondoo.com/ai-agent-security/skills/github/obra/superpowers/finishing-a-development-branch)

HTML

<a href="https://mondoo.com/ai-agent-security/skills/github/obra/superpowers/finishing-a-development-branch"><img src="https://mondoo.com/ai-agent-security/api/badge/github/obra/superpowers/finishing-a-development-branch.svg" alt="Mondoo Skill Check" /></a>

Image URL

https://mondoo.com/ai-agent-security/api/badge/github/obra/superpowers/finishing-a-development-branch.svg

Secure your AI agents

Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.

Continuous scanning of skills across all registries
Policy enforcement before skills reach your agents
Integration with your existing security workflow