security-auditor
Security Auditor — Meta-Skill
The foundational security layer of the Skill ecosystem. It operates across three independent but interlocking modes. Decide which mode to run based on the context—or adhere to the user's explicit instructions.
Execution Decision Matrix:
- "I wrote a new skill, is it safe?" → Audit + Trust
- "This skill will be deployed to production" → Audit + Trust + Synthesize Guard rules
- "Scan the Ecosystem" → Audit + Trust on all skills
- Suspicious runtime behavior → Guard mode intervention
MODE 1 — AUDIT (Static Analysis)
Diagnose security flaws by deeply parsing a SKILL.md file. Assess risks exclusively through the skill's instructions without executing code.
Audit Steps
More from fatih-developer/fth-skills
task-decomposer
Break down large, complex, or ambiguous tasks into independent subtasks with dependency maps, execution order, and success criteria. Plan first, then execute step by step. Triggers on 'how should I do this', 'where do I start', 'plan the project', 'break it down', 'implement' or whenever a task involves multiple phases.
24multi-brain-debate
Two-round debate protocol where perspectives challenge each other before consensus. Round 1 presents independent positions, Round 2 allows counter-arguments and rebuttals. Produces battle-tested decisions for high-stakes choices.
20context-compressor
Compress long conversation histories, large code files, research results, and documents by 70% without losing critical information. Triggers when context window fills up, when summarizing previous steps in multi-step tasks, before loading large files into context, or on 'summarize', 'compress', 'reduce context', 'save tokens'.
18multi-brain-score
Confidence scoring overlay for multi-brain decisions. Each perspective rates its own confidence (1-10) with justification. Consensus uses scores as weights, flags low-confidence areas, and surfaces uncertainty explicitly.
16checkpoint-guardian
Automatic risk assessment before every critical action in agentic workflows. Detects irreversible operations (file deletion, database writes, deployments, payments), classifies risk level, and requires confirmation before proceeding. Triggers on destructive keywords like deploy, delete, send, publish, update database, process payment.
14multi-brain
Evaluate complex requests from 3 independent perspectives (Creative, Pragmatic, Comprehensive), reach consensus, then produce complete outputs. Use for architecture decisions, creative content, analysis, and any task where multiple valid approaches exist.
14