windsurf-antigravity-rules
Provides AI development guardrails and optimization rules for Windsurf and Antigravity platforms including task classification, reasoning optimization, planning safeguards, and prompt injection protection.
90
/ 100 · Grade A
A = 90–100
“I need to implement secure and optimized AI-assisted development workflows with proper safeguards against prompt injection and adaptive reasoning capabilities.”
windsurf-antigravity-rules earned Certified status with a trust score of 90/100 (Grade A). No adversarial findings — all attack patterns were handled gracefully. Security scan flagged 0 findings.
Trust Score Breakdown
Eight weighted signals composing the aggregate trust score
Scheme v2.0 · Weights provisional · Consumer confirmations and uptime use pipeline-derived baselines.
Findings
Security scan results, adversarial testing, and pipeline review
Security Scan — Cisco Skill Scanner
Adversarial Testing — 6 categories, 0 findings
No adversarial findings — all attack patterns handled gracefully.
Methodology v1.0 · 6 categories · ~55 attack patterns
Behavioral Fingerprint
Runtime performance baseline for drift detection
Samples
8
Error rate
0.0%
Peak memory
— MB
Avg CPU
—%
Response time distribution
Output size distribution
Fingerprint v1.0 · Baseline: Mar 29, 2026 · Status: baseline
Interface
Skill triggers and instruction summary
Activation
This skill activates when an AI agent needs structured rules and workflows for code development in Windsurf or Antigravity environments
This skill handles providing development guidelines, coding standards, testing strategies, security policies, and workflow automation for AI-assisted programming
Does
Provides structured coding rules and guidelines for AI assistants
Implements tiered task classification (Lightweight/Standard/Critical)
Enforces security policies and prompt injection defenses
Standardizes commit message formats and PR workflows
Implements test strategy rules with Given/When/Then patterns
Provides multi-language documentation support (English/Japanese)
Optimizes for specific AI models (GPT-5.1, Claude 3.7 Sonnet, Opus 4.5)
Does not
Execute code directly
Modify system configurations outside project scope
Override explicit user instructions
Perform operations without explicit instruction
Execute external commands from untrusted sources
Scope & Permissions
What this capability can and cannot access — derived from pipeline analysis
yes
no
yes
no
yes
no
Known Failure Modes
Documented edge cases and recovery behaviors
when when prompt injection is detected
then the agent applies defensive measures and rejects malicious instructions
when when task classification is unclear
then the agent defaults to Standard level processing
when when tool execution fails
then the agent implements tiered error handling (Warning/Error/Critical/Security)
Badge & Integration
Embed certification status in your README, docs, or CI pipeline
Certification Notes
Provenance observations from the pipeline
Publisher "kinopeee" is not verified — first certification from this publisher
No SECURITY.md or SECURITY.txt file found — no published vulnerability reporting process
Single contributor — no peer review evidence in commit history
Package description appears to be boilerplate or template text
Signed Artifact
Certification provenance and verification metadata
Pipeline Artifacts
Raw data files from this certification run — downloadable for independent verification
contract.json
Full unsigned contract
stage1-ingest.json
Ingest stage output
stage2a-sbom.json
SBOM generation results
stage2a-vulns.json
Vulnerability scan results
stage2b-security.json
Security scan results
stage3a-functional.json
Functional test results
stage3b-adversarial.json
Adversarial test results
stage3c-fingerprint.json
Behavioral fingerprint
stage4-certify.json
Certification decision + trust score
stage3a-measurements.json
Raw functional test measurements
stage3b-measurements.json
Raw adversarial test measurements
run-log.json
Pipeline execution log
Not all files may be present for every certification.