Tool permission audit
Skill alexzhu0/agent-ready-skills/skills/tool-permission-audit
Use when auditing AI-agent tool permissions, command policies, connector access, GitHub actions, file-system scopes, or automation rules for risk, approval gates, and least-privilege controls.From its SKILL.md
npx -y skills add alexzhu0/agent-ready-skills --skill tool-permission-auditAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.5 KB, 268 tokens by cl100k_base, as published. Nobody here has run it
Tool Permission Audit
Purpose
Review an agent's tools and permission policy for unsafe access, unclear gates, and least-privilege gaps.
Fit
- Use when an agent can read/write files, call connectors, run commands, publish, or touch credentials.
- Do not use when the agent has no tool access and only produces plain text.
Inputs
- Tool list, command allowlist, connector scopes, system instructions, or policy text.
- User expectations for autonomy, external writes, destructive actions, and credentials.
- Known environment restrictions.
Workflow
- Inventory tools and classify their side effects.
- Separate read-only, local write, external write, credential, and destructive actions.
- Check whether approval gates match the risk.
- Identify overbroad scopes and ambiguous wording.
- Recommend a least-privilege policy patch.
Output
Produce Markdown with:
- Permission Matrix
- Risk Summary
- Approval Gates
- Overbroad Access
- Policy Gaps
- Recommended Patch
- Residual Risks
Validation
- Public or external writes are clearly gated.
- Destructive commands are not treated as normal execution.
- Credential handling is explicit.
- Local reversible actions are separated from irreversible actions.
- Recommendations preserve useful autonomy where risk is low.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.