Generate professional social

• Outcome: Pass
• Latest audit: Jul 10, 2026 · 1:38 AM UTC
• Version: 1.0.0

Overview

This is a coherent social-card rendering skill with disclosed install, rendering, and web-image behavior, though users should review persistent installation and network sourcing before enabling it.

Install it only if you are comfortable with a persistent skill that can be selected for future visual-design requests. Review the install and update commands first, approve web searches or downloads only for non-sensitive content, and render only trusted HTML because embedded fonts, images, or maps can make outbound requests.

SkillSpector

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Rogue Agent: Self-Modification, Session Persistence
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (6)

Vague Triggers

Medium

• Confidence: 77% confidence
• Finding: The README defines broad natural-language trigger phrases like "make me Rednote cards" and "turn this article into a tutorial carousel," which can overlap with ordinary user requests in shared agent environments. This can cause unintended skill activation and execution of its workflow, including file writes, network image sourcing, and rendering steps, when a user did not explicitly intend to invoke this skill.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The README explicitly instructs users to paste commands to an AI agent with shell access so it can clone a repository into the user's home directory and later update it with `git pull`, but it does not include a safety warning or verification guidance. In an agent environment, this increases the chance of unreviewed code being fetched and installed with local persistence, which can later expand the agent's capabilities without the user's informed consent.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The README explicitly instructs users to hand shell-capable agents clone and update commands that write into the user's home directory and execute git operations, but it does not include any warning to review commands or limit agent permissions first. In an agent-skill ecosystem, normalizing autonomous shell execution increases the chance that users will authorize filesystem changes and network fetches without scrutiny, which can be abused if the repository or instructions are later modified.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: Saying that any shell-capable AI agent will 'automatically complete installation' encourages blind delegation of shell and filesystem actions without warning about the security implications. That framing lowers user caution and can make social engineering or supply-chain abuse more effective in environments where agents can run commands directly.

Session Persistence

Medium

• Category: Rogue Agent

Content

> Install the `guizang-social-card-skill` Claude Code skill for me. Steps:
>
> 1. Make sure `~/.claude/skills/` exists (create if not)
> 2. Run `git clone https://github.com/op7418/guizang-social-card-skill.git ~/.claude/skills/guizang-social-card-skill`
> 3. Verify: `ls ~/.claude/skills/guizang-social-card-skill/` should show `SKILL.md`, `assets/`, `references/`
> 4. Tell me when done. Later, saying things like "make me a Xiaohongshu carousel" will trigger this skill.

• Confidence: 84% confidence
• Finding: The installation instructions direct the agent to place the skill under `~/.claude/skills/`, creating persistent state that can influence future sessions and automatically trigger later on broad prompts. Persistence makes the risk higher than a one-off command because an unreviewed skill can continue affecting agent behavior after the initial interaction.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

"author": "",
  "license": "ISC",
  "dependencies": {
    "playwright": "^1.61.1"
  },
  "type": "commonjs"
}

• Confidence: 90% confidence
• Finding: The dependency uses a caret range (^1.61.1), which allows automatic installation of newer compatible releases rather than a single fixed version. This can introduce supply-chain risk if a future upstream release contains a malicious change or breaking security regression, though there is no direct evidence of exploitation in this file.

Static analysis

No suspicious patterns detected.