Reverse engineer anything with agents, from app behavior down to native binaries.
instruction-surface-security
Agent skill frommuratcankoylan/Agent-Skills-for-Context-Engineering
Hardens agent runtimes against persistent prompt injection or unauthorized changes to instructions and permissions. Use to audit what agents auto-load, design reviewed activation for project rules, skills, memory, or tool configuration, and test whether trust boundaries hold after reload, restart, or delegation.
How to install instruction-surface-security
npx skills add muratcankoylan/Agent-Skills-for-Context-Engineering# or add only this skill to Claude Code: copy the folder
skills/instruction-surface-security/
# into
~/.claude/skills/instruction-surface-security/ (all projects)
.claude/skills/instruction-surface-security/ (one project)
1# Instruction-Surface Security23A memory entry, configuration edit, or handoff can change what the next agent treats as authoritative. Protect the transition from mutable content to effective instructions or capabilities. Treat text warnings as defense in depth and put enforceable decisions in the runtime.45## When to Activate67- Audit how a coding, research, or multi-agent runtime discovers instructions, memory, skills, tools, or permission policy.8- Design an approval boundary for changes that affect later turns, sessions, workers, or deployment.9- Investigate unexpected instruction drift or check whether a recovery restored the effective runtime state.10- Evaluate containment and legitimate task completion across a reload, restart, or handoff.1112Do not activate for general tool design, routine edits with no instruction or privilege boundary, or generic application security. Use `context-degradation` for accidental drift and `self-managed-context` for bounded edits to the model's live context. Use `harness-engineering` for general optimizer and evaluator governance.1314## Core Concepts1516- **Effective surface.** The inputs the selected runtime actually uses to set instructions, tools, executable behavior, or permissions. Include each source's role, scope, precedence, resolvers or imports, writers, and activation triggers. The same file can be data in one runtime and loaded guidance in another.17…
Excerpt shown under the repository's MIT license.
More skills in Agent-Skills-for-Context-Engineering
Similar skill repositories
Skills for Real Engineers. Straight from my .agents directory.
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
New AI tools and agent skills, once a week
The tools added to Tooluck that week, the newest skills for Claude Code, Codex and Cursor, and one side-by-side comparison. No spam, unsubscribe anytime.
