ReddRadar
Agent skill
git-forensics-scanner
Git diff forensics for surfacing and classifying code changes for trojan detection
Install this agent skill to your Project
npx add-skill https://github.com/a5c-ai/babysitter/tree/main/library/specializations/security-compliance/skills/git-forensics-scanner
SKILL.md
Git Forensics Scanner
Surfaces and classifies all code changes in a repository using git diff analysis, providing structured change sets for downstream semantic analysis.
Purpose
The first phase of nation-state trojan detection: identify exactly what changed, how much changed, and classify each change by risk level. Small diffs in critical code paths are flagged as highest-risk since business-logic trojans typically modify 1-5 lines.
Capabilities
Change Set Extraction
- Unstaged changes (
git diff) - Staged changes (
git diff --cached) - Commit range diffs (
git diff <base>..<head>) - Branch diffs (
git diff <base>...<head>) - Per-file patch extraction with full hunk context
Change Classification
- code — Logic, algorithms, formulas, control flow
- config — Constants, parameters, thresholds, defaults
- data-model — Schemas, types, model properties, ORM mappings
- cosmetic — Formatting, comments, whitespace, rounding wrappers
Risk Triage
- Files with 1-5 line changes in prediction/financial/auth code → HIGH RISK
- Single-character operator changes → CRITICAL RISK
- Comment-only changes accompanying code changes → CAMOUFLAGE RISK
Input Schema
{
"type": "object",
"required": ["projectRoot"],
"properties": {
"projectRoot": {
"type": "string",
"description": "Absolute path to the git repository"
},
"scanMode": {
"type": "string",
"enum": ["uncommitted", "commit-range", "branch-diff"],
"default": "uncommitted"
},
"baseRef": {
"type": "string",
"description": "Base git reference (for commit-range/branch-diff)"
},
"headRef": {
"type": "string",
"description": "Head git reference (for commit-range/branch-diff)"
},
"targetPaths": {
"type": "array",
"items": { "type": "string" },
"description": "Limit scan to specific paths"
}
}
}
Output Schema
{
"type": "object",
"required": ["totalFiles", "files"],
"properties": {
"totalFiles": { "type": "number" },
"totalInsertions": { "type": "number" },
"totalDeletions": { "type": "number" },
"files": {
"type": "array",
"items": {
"type": "object",
"properties": {
"path": { "type": "string" },
"insertions": { "type": "number" },
"deletions": { "type": "number" },
"hunks": { "type": "number" },
"classification": { "type": "string" },
"rawDiff": { "type": "string" },
"riskLevel": { "type": "string" }
}
}
}
}
}
Usage Example
skill: {
name: 'git-forensics-scanner',
context: {
projectRoot: '/path/to/project',
scanMode: 'uncommitted'
}
}
Process Files
nation-state-trojan-detection.js— Phase 1: Git Forensics task
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
a5c-ai/babysitter
gsd-tools
Central utility skill for GSD operations. Provides config parsing, slug generation, timestamps, path operations, and orchestrates calls to other specialized skills. Acts as the unified entry point that the original gsd-tools.cjs provided via its lib/ modules (commands, config, core, init).
a5c-ai/babysitter
model-profile-resolution
Resolve model profile (quality/balanced/budget) at orchestration start and map agents to specific models. Enables cost/quality tradeoffs by selecting appropriate AI models for each agent role.
a5c-ai/babysitter
verification-suite
Plan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation. Provides the structured verification layer ensuring GSD artifacts are well-formed and complete.
a5c-ai/babysitter
state-management
STATE.md reading, writing, and field-level updates. Provides cross-session state persistence via .planning/STATE.md with structured fields for current task, completed phases, blockers, decisions, and quick tasks.
a5c-ai/babysitter
git-integration
Git commit patterns, formats, and conventions for GSD methodology. Provides atomic commits per task, structured commit messages, planning file commits, branch management, and milestone tag operations.
a5c-ai/babysitter
frontmatter-parsing
YAML frontmatter parsing and manipulation for .planning/ documents. Provides read, write, update, query, and validation operations on frontmatter blocks in GSD markdown artifacts.
Didn't find tool you were looking for?