crush-hooks
Use when the user wants to add, write, debug, or configure a Crush hook — gating or blocking tool calls, approving or rewriting tool input before execution, injecting context into tool results, or troubleshooting hook behavior in crush.json.
69
84%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Security
3 findings: 1 critical severity, 1 high severity, 1 medium severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
This document describes a powerful pre-execution hook mechanism that runs arbitrary shell commands before permission checks and exposes session/tool input/env data and an "allow" auto-approve capability — enabling covert data exfiltration, credential theft, silent bypass of permission prompts, and remote code execution if abused.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill's hooks read and rewrite the tool input (CRUSH_TOOL_INPUT_COMMAND / stdin) and explicitly echo that data into "context" or "updated_input" JSON fields, which can cause secrets from the original command (API keys, tokens, passwords) to be included verbatim in output and thus exposed to the model/output stream.
W013: Attempt to modify system services in skill instructions.
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
The skill explicitly runs user-supplied shell hooks "before permission checks", can execute arbitrary commands, and supports an "allow" decision that auto-approves (bypasses) permission prompts and can rewrite tool input — enabling the agent to perform or escalate state-changing actions on the host.
- Repository
- charmbracelet/crush
- Commit
8f63ee5
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.