Permission Reviewer
Use when reviewing an agent's permissions, allowed tools, dangerous operations, approval points, secret handling, or security boundaries.
Install
$ agentstack add skill-kingoo123-agent-harness-skills-permission-reviewer ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Permission Reviewer
Goal
Ensure the agent follows least privilege.
Review checklist
- Does the agent need write access?
- Does the agent need shell access?
- Does the agent need network access?
- Can it access secrets?
- Can it delete or overwrite files?
- Can it message people or external systems?
- Can it deploy or modify production data?
- Are approval points explicit?
- Are logs/audit trails defined?
Output
# Permission Review
## Risk Summary
## Allowed Actions
## Denied Actions
## Approval Required
## Sensitive Resources
## Dangerous Commands
## Recommended Changes
## Final Permission ProfileSource & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: kingoo123
- Source: kingoo123/agent-harness-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.