Agent skill · AI & Agents

semantic-code-analyzer

LLM-powered semantic analysis of code diffs to detect business-logic trojans

a5c-aigithub.com/a5c-aiGitHub ↗
claude-codecodexcan modify filesMIT
Install
npx skills add a5c-ai/babysitter --skill semantic-code-analyzer --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 5 KB
Bundled scripts: none
Allowed tools: -Bash-Read-Glob-Grep
Path: library/specializations/security-compliance/skills/semantic-code-analyzer/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 1,642
Language: JavaScript

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Semantic Code Analyzer LLM-powered semantic analysis engine that detects business-logic trojans by comparing code intent (docstrings, function names, variable names) against actual implementation behavior. ## Purpose The core detection capability of nation-state trojan detection. Traditional SAST tools check syntax; this skill checks **semantics** — whether the code does what it claims to do. It catches operator substitutions, logic inversions, constant manipulation, narrative camouflage, and compound self-masking attacks. ## Capabilities ### Intent vs Implementation Analysis - Reads function names, docstrings, and variable names to establish **intent** - Traces code execution to determine **actual behavior** - Flags any contradiction as a potential trojan indicator ### Mathematical Verification - Plugs concrete values into changed formulas - Computes before/after results to quantify impact - Detects ratio inversions (a/b vs b/a), precision loss (/ vs //), and threshold shifts ### Docstring Contradiction Detection - Compares narrative claims in comments/docstrings against code behavior - Detects narrative camouflage where docs are updated to match malicious code - Cross-reference

What's inside
Steps it walks through
  1. Purpose
  2. Capabilities
  3. Intent vs Implementation Analysis
  4. Mathematical Verification
  5. Docstring Contradiction Detection
  6. Test Evasion Analysis
  7. Blast Radius Mapping
  8. Input Schema
  9. Output Schema
  10. Usage Example
  11. Attack Signatures Detected
  12. Process Files
Ships with 1 file
  • README.md
More from babysitter
All skills →
About this skill
What does the semantic-code-analyzer skill do?

LLM-powered semantic analysis of code diffs to detect business-logic trojans

How do I install it?

Run `npx skills add a5c-ai/babysitter --skill semantic-code-analyzer --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From a5c-ai/babysitter, a repository with 1,642 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going