The Agent Skills Directory

[SAFE] (SAFE): The skill serves as a security-enhancing utility for developers.
Input Sanitization: Example scripts like validate-bash.sh and validate-write.sh demonstrate how to parse agent input via jq and apply regex checks to block destructive operations and path traversal.
Secure Execution: The scripts/test-hook.sh utility implements defensive coding by validating file paths against shell-metacharacters and using positional parameters in bash -c calls to prevent command injection.
Linter Enforcement: scripts/hook-linter.sh scans hook scripts for security pitfalls, including unquoted variables and hardcoded absolute paths.
No Malicious Patterns: Analysis of the scripts and documentation found no evidence of data exfiltration, obfuscation, or unauthorized remote code execution.

hook-development