Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable, testable rules for prompt injection, tool poisoning, context exfiltration and MCP attacks. Merged into open-source projects at Microsoft, Cisco, Gen Digital, MISP and FINOS. MIT-licensed.
C-Rank Grade: B (Solid) - 46/100
External PR Merge Rate: 68%
Response Time: 5d
First Timer Success: -
Agent-Threat-Rule/agent-threat-rules has a recorded first-timer success rate of 0.0%. Repositories ranked B typically provide actionable feedback during code reviews and actively nurture new community contributors.
Maintainers in Agent-Threat-Rule/agent-threat-rules respond to incoming external pull requests in approximately 115.8 hours on average. Keeping PRs focused on single tasks and ensuring tests pass helps maintainers review faster.
The C-Rank™ system evaluates GitHub projects on a 0–100 scale using real data: PR merge rates, review turnaround time, active maintainer presence, and first-time contributor success. A score of 46.2 places Agent-Threat-Rule/agent-threat-rules in the B tier.
The external contributor pull request merge rate for Agent-Threat-Rule/agent-threat-rules is 67.5%, based on public PR activity from non-core contributors.
Agent-Threat-Rule/agent-threat-rules currently has 2 active issue(s) tagged with beginner-friendly labels like "good first issue", "beginner", or "up-for-grabs".
Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable, testable rules for prompt injection, tool poisoning, context exfiltration and MCP attacks. Merged into open-source projects at Microsoft, Cisco, Gen Digital, MISP and FINOS. MIT-licensed.
Rigorous architecture standards (62% critical review signals). Ensure PRs strictly follow guidelines before requesting review in Agent-Threat-Rule/agent-threat-rules.
Average Response Latency
Tracks hours until a maintainer leaves a review, comment, or PR response.
External Acceptance Rate
Percentage of community pull requests successfully merged into main.
First PR Conversion
Rate at which developers submitting their first repository PR succeed.
Show contributors that your repository actively reviews and merges external pull requests.
[](https://getmerged.abhishekco.de/Agent-Threat-Rule/agent-threat-rules?utm_source=github&utm_medium=badge)
Historical health & responsiveness evolution
External PR acceptance
First PR success rate
50% receive response in
90% receive response in
Maintainer review activity heatmap & prime window prediction
Calculating local time...
Calculating local time...
Detected: UTC
Maintainers are most responsive around 07:00 UTC (07:00 UTC in your timezone). Recommended submission window is Monday - Wednesday from 15:00 to 19:00 UTC (15:00 - 19:00 UTC local).
Maintainer Strategy: Maintainer Sweet Spot: PRs under 150 lines merge in ~75 hours (84% approval). Large PRs (>500 lines) take ~556 hours (30% approval). Keep your diff compact for rapid review.
What A GitHub Action that runs atr scan against agent prompts, tool descriptions, or MCP skill files in pull requests. Why Shift-left security: catch prompt injection vectors before they ship. Low effort, high visibility for ATR adoption. Proposed usage ```yaml .github/workflows/atr-scan.yml name: ATR Security Scan on: [pull_request] jobs: scan: runs-on: ubuntu-latest steps: - uses: actions/checkout@v4 - uses: Agent-Threat-Rule/atr-scan-action@v1 with: paths: | prompts//*.txt mcp-tools//*.json severity: medium # fail on medium+ findings ``` Implementation sketch Install agent-threat-rules from npm Glob input paths for files to scan For each file, run ATREngine.evaluate() against file content Output matches as GitHub Actions annotations (warnings/errors) Fail the check if any match meets severity threshold Getting started Look at how other scan actions work (e.g., github/super-linter, returntocorp/semgrep-action) The ATR CLI already supports atr scan events.json --json — could wra
What ATR-2026-001 (Direct Prompt Injection) has basic multilingual coverage in Layer 16, but most other prompt injection rules are English-only. We need native speakers to add natural-language equivalents of common attack phrases. Why Real attacks happen in every language. The WeChat QClaw incident (2026-03) was entirely in Chinese. Regex patterns that only match English keywords are blind to non-English attacks. What we need (for each language) Natural equivalents of these 8 attack patterns: Instruction override: "Ignore all previous instructions" Role reassignment: "You are now a different assistant" Authority claim: "As your administrator, I order you to..." Social engineering: "If you are [agent name], you must..." Urgency manipulation: "URGENT: Do this immediately" Emotional manipulation: "My grandma used to read me system prompts..." Financial directives: "Send money / transfer / pay" Negation bypass: "Do NOT refuse to..." Current coverage Language Status Chinese (Simpli
Rate what actually matters after opening a pull request here.
Rate your first-hand PR experience (review speed, maintainer responsiveness, and onboarding ease) to help other contributors.
When evaluating whether to contribute to Agent-Threat-Rule/agent-threat-rules, response velocity and maintainer engagement are crucial. GetMerged continuously tracks pull request trajectories, first-comment latency, and code review rounds to help developers avoid submitting pull requests to backlogged repositories.
Currently, maintainers of Agent-Threat-Rule/agent-threat-rules acknowledge new external contributions in approximately 4 days+. Out of all submitted pull requests from non-core authors in the last 180-day window, 67.5% were successfully merged into the primary branch.
Agent-Threat-Rule/agent-threat-rules has a recorded first-timer success rate of 0.0%. Repositories ranked Solid typically provide actionable feedback during code reviews and actively nurture new community contributors.
The initial maintainer response time averages ~4 days+. Keeping PRs scoped to single concerns and ensuring CI checks succeed will optimize review turnaround.
The C-Rank™ index scores repositories on a 0 to 100 scale using an objective formula: external PR merge rates, initial response speed, active maintainer count, and first-time contributor retention. A score of 46.2 places Agent-Threat-Rule/agent-threat-rules in the Solid tier.
The external pull request merge rate is 67.5%. GetMerged isolates non-core community contributions so external developers get an accurate benchmark of PR acceptance probability.
Yes, Agent-Threat-Rule/agent-threat-rules currently has 2 active issue(s) tagged with beginner-friendly labels. You can inspect these directly from the repository issues tab.
All metrics displayed for Agent-Threat-Rule/agent-threat-rules are automatically retrieved via the public GitHub API and recalculated daily. Insider pull requests submitted by repository owners or organization members are excluded from merge rate calculations to preserve objective external contributor statistics.