RRepoGEO

REPOGEO REPORT · LITE

affaan-m/agentshield

Default branch main · commit 25d91f00 · scanned 6/6/2026, 1:46:38 AM

GitHub: 803 stars · 171 forks

AI VISIBILITY SCORE
40 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
2 pass · 0 warn · 0 fail
Objective metadata checks
AI knows your name
3 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface affaan-m/agentshield, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • hightopics#1
    Expand GitHub topics to include broader security and deployment terms

    Why:

    CURRENT
    ai-agent, anthropic, claude-code, hackathon, mcp, opus, security
    COPY-PASTE FIX
    ai-agent, security, ai-security, agent-security, llm-security, vulnerability-scanner, prompt-injection, cli, github-action, anthropic, claude-code
  • highreadme#2
    Reposition the README's opening to emphasize its role as a dedicated AI agent security scanner tool

    Why:

    CURRENT
    Security auditor for AI agent configurations Scans Claude Code setups for hardcoded secrets, permission misconfigs, hook injection, MCP server risks, and agent prompt injection vectors.
    COPY-PASTE FIX
    AgentShield is a dedicated security scanner for AI agent configurations. It automatically detects vulnerabilities in agent setups, MCP servers, and tool permissions, including hardcoded secrets, permission misconfigurations, hook injection, and prompt injection vectors. Available as a CLI, GitHub Action, and GitHub App integration, AgentShield provides a crucial layer of defense for your AI agents.
  • mediumabout#3
    Refine the 'About' description to explicitly state it's a vulnerability scanning tool

    Why:

    CURRENT
    AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️
    COPY-PASTE FIX
    AgentShield is an AI agent security vulnerability scanning tool. It detects critical vulnerabilities in agent configurations, MCP servers, and tool permissions, including prompt injection and data exfiltration risks. Available as a CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface affaan-m/agentshield
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
OWASP AI Exchange (AIX)
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. OWASP AI Exchange (AIX) · recommended 1×
  2. Microsoft Azure AI Security Checklist · recommended 1×
  3. IBM AI Governance Toolkit · recommended 1×
  4. Google Cloud AI Security Best Practices · recommended 1×
  5. Fiddler AI · recommended 1×
  • CATEGORY QUERY
    How to audit my AI agent configurations for security vulnerabilities and risks?
    you: not recommended
    AI recommended (in order):
    1. OWASP AI Exchange (AIX)
    2. Microsoft Azure AI Security Checklist
    3. IBM AI Governance Toolkit
    4. Google Cloud AI Security Best Practices
    5. Fiddler AI
    6. Adversarial Robustness Toolbox (ART)
    7. DeepMind's AI Safety Research

    AI recommended 7 alternatives but never named affaan-m/agentshield. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    CLI or GitHub Action to scan AI agent code for secrets and permissions?
    you: not recommended
    AI recommended (in order):
    1. GitGuardian (GitGuardian/ggshield)
    2. TruffleHog (trufflesecurity/trufflehog)
    3. Semgrep (semgrep/semgrep)
    4. detect-secrets (Yelp/detect-secrets)
    5. Gitleaks (gitleaks/gitleaks)
    6. Snyk Code (snyk/snyk)
    7. Checkov (bridgecrewio/checkov)

    AI recommended 7 alternatives but never named affaan-m/agentshield. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    pass

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of affaan-m/agentshield?
    pass
    AI named affaan-m/agentshield explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts affaan-m/agentshield in production, what risks or prerequisites should they evaluate first?
    pass
    AI named affaan-m/agentshield explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo affaan-m/agentshield solve, and who is the primary audience?
    pass
    AI named affaan-m/agentshield explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of affaan-m/agentshield. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/affaan-m/agentshield.svg)](https://repogeo.com/en/r/affaan-m/agentshield)
HTML
<a href="https://repogeo.com/en/r/affaan-m/agentshield"><img src="https://repogeo.com/badge/affaan-m/agentshield.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

affaan-m/agentshield — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite