SkillShield: Prompt-Space Security Skills for LLM Coding Agents

arXiv:2608.25817 · cs.CR · Submitted 2026-08-26 · Read on arXiv

cs.CR

Submitted: 2026-08-26

Updated: 2026-08-26

Code: https://github.com/anomalyco/opencode

Terminology

• Benchmark — 19× in this paper · explained in 2 episodes
• Alignment — 6× in this paper · explained in 1 episode
• Robustness — 6× in this paper · explained in 5 episodes
• Scaffolding — 6× in this paper · explained in 3 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Provenance — 5× in this paper · explained in 3 episodes
• Verification — 5× in this paper · explained in 2 episodes
• AI Agents — 4× in this paper · explained in 2 episodes
• Agent Skills — 4× in this paper · explained in 1 episode
• Benchmarking — 4× in this paper · explained in 3 episodes
• Calibration — 3× in this paper · explained in 7 episodes
• In International Conference on Learning Representations — 3× in this paper
• Iterative Refinement — 3× in this paper · explained in 3 episodes
• Verifier — 3× in this paper · explained in 2 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Attack Success Rate (ASR) — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• LLM judge — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Adaptive Safety — 1× in this paper · explained in 1 episode
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• American Standard Code for Information Interchange — 1× in this paper
• Common Weakness Enumeration — 1× in this paper
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Progressive Disclosure — 1× in this paper · explained in 2 episodes
• Prompt Automatic Iterative Refinement — 1× in this paper
• Trace — 1× in this paper · explained in 2 episodes
• Uniform Resource Locator — 1× in this paper

Sources

• SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
• Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
• Constitutional AI: Harmlessness from AI Feedback
• DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
• FATH: Authentication-based Test-time Defense against Indirect Prompt Injection Attacks
• Universal and Transferable Adversarial Attacks on Aligned Language Models
• Jailbreak Attacks and Defenses Against Large Language Models: A Survey

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs