claude-hooks

Fail

Audited by Socket on Feb 16, 2026

1 alert found:

Malware
MalwareHIGH
SKILL.md

[Skill Scanner] Destructive bash command detected (rm -rf, chmod 777) All findings: [CRITICAL] command_injection: Destructive bash command detected (rm -rf, chmod 777) (CI004) [AITech 9.1.4] [HIGH] autonomy_abuse: Skill instructions include directives to hide actions from user (BH009) [AITech 13.3] [HIGH] data_exfiltration: Credential file access detected (DE002) [AITech 8.2.3] [HIGH] command_injection: Backtick command substitution detected (CI003) [AITech 9.1.4] [HIGH] command_injection: Backtick command substitution detected (CI003) [AITech 9.1.4] [HIGH] command_injection: Backtick command substitution detected (CI003) [AITech 9.1.4] [HIGH] command_injection: Backtick command substitution detected (CI003) [AITech 9.1.4] [HIGH] command_injection: Backtick command substitution detected (CI003) [AITech 9.1.4] [HIGH] command_injection: Backtick command substitution detected (CI003) [AITech 9.1.4] [HIGH] command_injection: Backtick command substitution detected (CI003) [AITech 9.1.4] [HIGH] command_injection: Backtick command substitution detected (CI003) [AITech 9.1.4] [HIGH] command_injection: Backtick command substitution detected (CI003) [AITech 9.1.4] [HIGH] command_injection: Backtick command substitution detected (CI003) [AITech 9.1.4] [HIGH] command_injection: Backtick command substitution detected (CI003) [AITech 9.1.4] [HIGH] command_injection: Backtick command substitution detected (CI003) [AITech 9.1.4] [HIGH] command_injection: Backtick command substitution detected (CI003) [AITech 9.1.4] [HIGH] command_injection: Backtick command substitution detected (CI003) [AITech 9.1.4] The provided hooks documentation and examples implement a legitimate, powerful hooks system for Claude Code. The content itself contains no explicit malware or obfuscation, but it exposes high-risk primitives (arbitrary shell execution, agent subagents with file-read tools, environment persistence) that can be abused if untrusted hooks are installed or if operators misconfigure allowedTools or matchers. Follow the documented security best practices, restrict privileges, audit third-party hooks, and consider sandboxing or egress controls to mitigate exfiltration and persistence risks.

Confidence: 95%Severity: 90%
Audit Metadata
Analyzed At
Feb 16, 2026, 11:17 AM
Package URL
pkg:socket/skills-sh/outfitter-dev%2Fagents%2Fclaude-hooks%2F@c6ea39683019e33574b55ed969a90a2babd7e376