AI Tool Permissions Review
Compare each tool capability manifest with an explicit allowlist and report unapproved permission strings.
$5
Works with the AI Agents you already use
AI Tool Permissions Review
Example session with this skill installed
Run AI Tool Permissions Review on the captured artifacts in ./artifacts and tell me what fails before we release.
- Read your context and instructions
- Compiled the ai tool permissions
Summary
Ran AI Tool Permissions Review on the bundled defect example. Findings from the generated report:
Counts: fail 1, info 1
FAIL permission.excess_scope: tool send_email requests mail:send, not in the allowlist (P1). Matching is exact; wildcards are not expanded.
Next steps
- Fix the FAIL items above.
- Re-run on the corrected input and compare the issue delta.
- Share report.html with your team or client.
Connects securely to your tools. The creator never sees your data.
About this skill
What it does
Compare each tool capability manifest with an explicit allowlist and report unapproved permission strings.
Included (v0.2.0)
- SKILL.md workflow for Claude Code and other agents
- Editable Python analyzer
- HTML, JSON, CSV and Markdown reports
- Defect and corrected examples with before/after comparison
- Executable self-tests
Limits
Static manifest review cannot prove runtime isolation or catch undeclared capabilities.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 4 days ago
Requires