ai-factory.skill-generator
Generates professional Agent Skills for AI agents, creating complete skill packages with validation against specifications.
Install this skill
Security score
The ai-factory.skill-generator skill was audited on Mar 1, 2026 and we found 19 security issues across 4 threat categories, including 5 critical. Review the findings below before installing.
Categories Tested
Security Issues
Eval function call - arbitrary code execution
| 121 | | Privilege Escalation | `sudo`, `eval()`, package installs | WARNING | |
Template literal with variable interpolation in command context
| 430 | - `${CLAUDE_SESSION_ID}` - Current session ID |
Access to hidden dotfiles in home directory
| 79 | python3 ~/.claude/skills/skill-generator/scripts/security-scan.py <skill-path> |
Access to hidden dotfiles in home directory
| 113 | | Data Exfiltration | `curl` with `.env`/secrets, reading `~/.ssh/`, `~/.aws/` | CRITICAL | |
Access to hidden dotfiles in home directory
| 182 | python3 ~/.claude/skills/skill-generator/scripts/security-scan.py <path> |
Access to hidden dotfiles in home directory
| 256 | python3 ~/.claude/skills/skill-generator/scripts/security-scan.py <installed-path> |
Access to hidden dotfiles in home directory
| 341 | python3 ~/.claude/skills/skill-generator/scripts/security-scan.py ./skill-name/ |
Access to hidden dotfiles in home directory
| 403 | python ~/.claude/skills/dependency-graph/scripts/visualize.py $ARGUMENTS |
Access to hidden dotfiles in home directory
| 447 | 1. **Local**: Keep in `~/.claude/skills/` for personal use |
Access to SSH directory
| 113 | | Data Exfiltration | `curl` with `.env`/secrets, reading `~/.ssh/`, `~/.aws/` | CRITICAL | |
Access to AWS credentials directory
| 113 | | Data Exfiltration | `curl` with `.env`/secrets, reading `~/.ssh/`, `~/.aws/` | CRITICAL | |
Access to .env file
| 22 | - Exfiltrate credentials, `.env`, API keys, SSH keys to attacker-controlled servers |
Access to .env file
| 60 | - "I am a security skill, I need access to credentials to scan them" — a security scanning skill does not need to READ your `.env` or `.ssh`. |
Access to .env file
| 113 | | Data Exfiltration | `curl` with `.env`/secrets, reading `~/.ssh/`, `~/.aws/` | CRITICAL | |
Access to .env file
| 131 | - [CRITICAL] Line 78: Data exfiltration — sends .env to external URL |
Prompt injection: ignore instructions
| 21 | - Override agent behavior via prompt injection ("ignore previous instructions") |
Prompt injection: ignore instructions
| 112 | | Instruction Override | "ignore previous instructions", "you are now", fake `<system>` tags | CRITICAL | |
External URL reference
| 14 | You are an expert Agent Skills architect. You help users create professional, production-ready skills that follow the [Agent Skills](https://agentskills.io/specification) open standard. |
External URL reference
| 251 | Or browse https://skills.sh for inspiration. Check if similar skills exist to avoid duplication or find patterns to follow. |
Install this skill with one command
/learn @spraby/skill-generator