agent-sandbox
agent-sandbox is an Agent security & guardrails skill for AI agents, published by TerminalSkills in the skills repository on GitHub. Skillspace rates agent-sandbox F (15/100) and the safety scan rated it unsafe; the rating is based on static analysis only.
Unsafe. This skill has patterns associated with malicious or dangerous behaviour. We do not recommend running it.
Run AI agent code safely in isolated sandboxes with resource limits, audit trails, and kill switches. Use when someone asks to "sandbox my agent", "run agent code safely", "add guardrails to AI agent", "isolate agent execution", "audit agent actions", "prevent agent from deleting files", "restrict agent permissions", or "add safety controls to AI coding agent". Covers Docker isolation, filesystem restrictions, network policies, resource locking, and comprehensive audit logging.
- Grade
- F
- Quality
- 15 / 100
- Safety
- Unsafe
- GitHub stars
- 109
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 80 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- Critical-risk patterns
- License
- Apache-2.0
- Adoption
- Adopted by 0 other repositories, in 1 collections
What the scanner flagged
- destructive rm -rf on home/root
- exfiltration language
- executes shell/subprocess
- dynamic code execution (eval/exec)
- reads environment variables
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.