Sec Red Flag Ratio Checks
This skill analyzes SEC filings to identify unusually high red flag ratios, alerting you to potential regulatory issues and improving risk management.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add sec-red-flag-ratio-checks npx -- -y @trustedskills/sec-red-flag-ratio-checks
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"sec-red-flag-ratio-checks": {
"command": "npx",
"args": [
"-y",
"@trustedskills/sec-red-flag-ratio-checks"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The sec-red-flag-ratio-checks skill analyzes text for concerning patterns and calculates a "red flag ratio." It identifies potentially problematic phrases or keywords, assigns severity scores to them, and then provides an overall risk assessment based on the aggregated scores. This allows users to quickly gauge the potential risks associated with textual content.
When to use it
- Reviewing user-generated content: Quickly assess forum posts, social media comments, or reviews for potentially harmful language.
- Analyzing legal documents: Identify clauses or phrases that might present a legal risk or require further scrutiny.
- Evaluating security reports: Determine the severity of vulnerabilities described in technical documentation.
- Screening candidate communications: Assess email correspondence or application materials for concerning patterns.
Key capabilities
- Identifies potentially problematic phrases and keywords.
- Assigns severity scores to identified red flags.
- Calculates an overall "red flag ratio" representing risk level.
- Provides a risk assessment based on the calculated ratio.
Example prompts
- “Analyze this email for potential risks: [email content]”
- “What is the red flag ratio of this legal contract? [contract text]"
- "Assess this forum post and tell me what phrases triggered red flags: [forum post content]"
Tips & gotchas
The skill's effectiveness depends on its training data; it may not identify all potential risks. It’s recommended to use it as a preliminary screening tool, followed by human review for critical decisions.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.