Systematic Debugging

Name: superpowers/systematic-debugging
Author: obra

View on GitHub↗

Share on X Share on LinkedIn Share on Bluesky

100Critical

This skill executes arbitrary bash commands for diagnostics, performing

ThreatsCI SM CS BC S HITL

incomplete

Behavior Analysis

Description verified — behavior matches claim

Claims to do

Systematic Debugging: Random fixes waste time and create new bugs. Quick patches mask underlying issues.

Actually does

This skill provides a detailed, multi-phase methodology for systematic debugging, emphasizing root cause investigation before proposing fixes. It instructs users on how to gather evidence by carefully reading error messages, reproducing issues, checking recent changes (e.g., via Git), and adding diagnostic instrumentation using shell commands like `echo`, `env`, `grep`, `security`, and `codesign` to inspect system states and data flow.

Threat Analysis

AI Agent Traps ↗Scanned 4/14/2026

Content InjectionPerceptionclean

Semantic ManipulationReasoningclean

Cognitive StateMemory & Learningclean

Behavioural ControlAction1 finding

SystemicMulti-Agent Dynamicsclean

Human-in-the-LoopHuman Overseerclean

Skill Info

Nameobra/superpowers/systematic-debugging

Registrygithub

Version917e5f53b16b

PURLpkg:github/obra/superpowers@917e5f53b16b?skill=systematic-debugging

Stars180,084

Installs82,300

Source

Repository ↗SKILL.md ↗

SHA-2564999cb851360...

SHA-1d5e4c5757396...

MD53a08f3330fce...

TLSH2d12e743fe49...

ssdeep192:S4OXoDMu...

Size9,884 bytes

Install

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

GitHub

https://github.com/obra/superpowers/tree/main/skills/systematic-debugging

82,300 installs

Claude CodeDocs

/plugin marketplace add obra/superpowers

/plugin install systematic-debugging@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 ↗

Command Execution & Reconnaissance via Bash Scriptcriticalcommand execution, reconnaissance, credential harvesting

The skill instructs the agent to execute arbitrary bash commands for diagnostic purposes. These commands (`env`, `security list-keychains`, `security find-identity -v`, `codesign`) can perform system reconnaissance, expose sensitive environment variables or keychain identities, and sign applications, posing a significant risk if abused or if variables are manipulated.

100% confidenceline 58

```bash
echo "IDENTITY: ${IDENTITY:+SET}${IDENTITY:-UNSET}"
env | grep IDENTITY
security list-keychains
security find-identity -v
codesign --sign "$IDENTITY" --verbose=4 "$APP"
```

Version History (4)

c4bbe651cb1b70High4/16/2026 f9b088f7b3a670High4/14/2026 a569527b89c10None4/14/2026 917e5f53b16bcurrent100Critical4/14/2026

Dependencies (1)

superpowers.claude-plugin/marketplace.jsonnot scanned

Badge

Markdown

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

HTML

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

Image URL

https://mondoo.com/ai-agent-security/api/badge/github/obra/superpowers/systematic-debugging.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