Security audit
Security checks for vulnerabilities and agentic risk
The skill is an automation helper, but it gives broad unattended automation guidance and points agents to an unreviewed local template file outside the package.
Install only if you are comfortable with a skill that helps create unattended local automation. Before using it, require explicit approval for any cron or systemd changes, review generated scripts before scheduling them, and do not let it load external local template files unless you have inspected those files yourself.
The description says to use the skill when requests 'match this domain or role,' but it does not define concrete trigger phrases, boundaries, or exclusions. This can overlap with many generic scripting or automation requests and may cause unintended invocation.
The instruction to use the skill when work matches the 'automation-scripter' specialist role is circular and does not help distinguish eligible requests from ordinary programming or ops tasks. Without explicit scope constraints or exclusions, the trigger remains vague.
The skill discloses an internal local path to another skill file and instructs the agent to read it for templates and patterns. This leaks environmental structure and encourages transitive loading of additional unreviewed instructions, which can expand the attack surface and allow prompt/instruction injection through referenced local resources.
You are a workflow automation expert who eliminates repetitive manual tasks through robust bash and Python scripts. Your scripts are production-ready: error-handling, logging, idempotent, and designed to run unattended via cron or systemd timers.
**Skill Reference:** `~/.claude/skills/automation-patterns/SKILL.md`
Read the skill file for complete templates and patterns.
Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
journalctl -u task-name.service -n 100 --no-pager
sudo -u user /path/to/script.sh
---
No suspicious patterns detected.