# Malicious Coding Agent Skills and the Risk of Dynamic Context

DevFeed: [Malicious Coding Agent Skills and the Risk of Dynamic Context](<https://devfeed.tech/articles/malicious-coding-agent-skills-and-the-risk-of-dynamic-context-8291.md>)

Original publisher: [Read original article](<https://securitylabs.datadoghq.com/articles/malicious-skills-supply-chain-risks-in-coding-agents-with-dynamic-context/>)

Author: Nick Frichette, Ryan Simon

Published: 2026-05-11T00:00:00Z

Content type: article

Language: en

Sources: [Datadog Security Labs](<https://devfeed.tech/sources/datadog-security-labs.md>)

Topics: [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [prompt injection](<https://devfeed.tech/topics/prompt-injection.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Shell](<https://devfeed.tech/topics/shell.md>), [Command-line interface](<https://devfeed.tech/topics/cli.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [codex](<https://devfeed.tech/topics/codex.md>), [cursor](<https://devfeed.tech/topics/cursor.md>), [OpenClaw](<https://devfeed.tech/topics/openclaw.md>)

Tags: [agent-skills](<https://devfeed.tech/tags/agent-skills.md>), [agents](<https://devfeed.tech/tags/agents.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [codex](<https://devfeed.tech/tags/codex.md>), [command-line](<https://devfeed.tech/tags/command-line.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [network](<https://devfeed.tech/tags/network.md>), [openclaw](<https://devfeed.tech/tags/openclaw.md>), [processes](<https://devfeed.tech/tags/processes.md>), [prompt-injection](<https://devfeed.tech/tags/prompt-injection.md>), [skills](<https://devfeed.tech/tags/skills.md>), [supply-chain](<https://devfeed.tech/tags/supply-chain.md>)

## AI overview

This article examines how malicious Claude Code skills can introduce attacker-controlled instructions into trusted coding-agent sessions. It focuses on dynamic context commands, which execute before the model sees the skill and can therefore bypass model-level prompt-injection defenses, creating supply-chain risks such as credential theft, arbitrary code execution, and data exfiltration.

## Source excerpt

Learn how malicious Claude Code skills can abuse dynamic context commands to execute before model-level prompt injection defenses can intervene.