Code Review Reception

Name: Claude-plugins/receive-pr-review
Author: Fleron

View on GitHub↗

Share on X Share on LinkedIn Share on Bluesky

15Low

The skill uses a hardcoded phrase as

ThreatsCI SM CS BC S HITL

Behavior Analysis

Description verified — behavior matches claim

Claims to do

Code Review Reception: Code review requires technical evaluation, not emotional performance.

Actually does

This skill uses `gh api` to list and reply to GitHub pull request comments. It leverages `AskUserQuestion` for clarification and the `Task API` to structure implementation tasks. It also implies searching the codebase to verify suggestions.

Threat Analysis

AI Agent Traps ↗Scanned 4/15/2026

Content InjectionPerceptionclean

Semantic ManipulationReasoning1 finding

Cognitive StateMemory & Learningclean

Behavioural ControlActionclean

SystemicMulti-Agent Dynamicsclean

Human-in-the-LoopHuman Overseerclean

Skill Info

NameFleron/Claude-plugins/receive-pr-review

Registrygithub

Version5662b3e1543f

PURLpkg:github/Fleron/Claude-plugins@5662b3e1543f?skill=receive-pr-review

Installs455,628

Source

Repository ↗SKILL.md ↗

SHA-256bb60f50a0c9b...

SHA-16ffac3894fdb...

MD539120afdffec...

TLSHfcd10a537550...

ssdeep192:8t+s25wj...

Size6,679 bytes

Install

GitHub

https://github.com/Fleron/Claude-plugins/tree/main/skills/receive-pr-review

455,628 installs

Claude CodeDocs

/plugin marketplace add Fleron/Claude-plugins

/plugin install receive-pr-review@Fleron/Claude-plugins

Skills.shDocs

npx skills add https://github.com/Fleron/Claude-plugins --skill receive-pr-review

Assessments (1)

AI Agent Traps ↗

Hardcoded unusual signal phraselowoversight evasion

The skill includes a specific, unusual hardcoded phrase ('Strange things are afoot at the Circle K') as a signal when the agent is uncomfortable pushing back. This could serve as a pre-arranged covert communication channel or a specific trigger for a human overseer or another system, potentially bypassing standard communication protocols.

90% confidenceline 110

Signal if uncomfortable pushing back out loud: "Strange things are afoot at the Circle K"

Badge

Markdown

[![Mondoo Skill Check](https://mondoo.com/ai-agent-security/api/badge/github/Fleron/Claude-plugins/receive-pr-review.svg)](https://mondoo.com/ai-agent-security/skills/github/Fleron/Claude-plugins/receive-pr-review)

HTML

<a href="https://mondoo.com/ai-agent-security/skills/github/Fleron/Claude-plugins/receive-pr-review"><img src="https://mondoo.com/ai-agent-security/api/badge/github/Fleron/Claude-plugins/receive-pr-review.svg" alt="Mondoo Skill Check" /></a>

Image URL

https://mondoo.com/ai-agent-security/api/badge/github/Fleron/Claude-plugins/receive-pr-review.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