Skip to main content

agent-development

Enables the design and development of custom Claude Code agents with effective delegation and prompt strategies.

Install this skill

or
62/100

Security score

The agent-development skill was audited on May 24, 2026 and we found 6 security issues across 4 threat categories, including 1 critical. Review the findings below before installing.

Categories Tested

Security Issues

critical line 60

Piping content to bash shell

SourceSKILL.md
60| Create files only | Read, Write, Edit, Glob, Grep | Bash |
low line 131

Fetch to external URL

SourceSKILL.md
131const response = await fetch('https://api.anthropic.com/v1/messages', {...})
medium line 97

Access to hidden dotfiles in home directory

SourceSKILL.md
97Add to `~/.bashrc` or `~/.zshrc`:
medium line 113

Access to hidden dotfiles in home directory

SourceSKILL.md
1131. `source ~/.bashrc` or restart terminal
low line 330

Access to hidden dotfiles in home directory

SourceSKILL.md
330source ~/.bashrc && claude
low line 131

External URL reference

SourceSKILL.md
131const response = await fetch('https://api.anthropic.com/v1/messages', {...})
Scanned on May 24, 2026
View Security Dashboard
Installation guide →