- Home
- Skills
- APIs & Backend
- OAuth Permission Expansion & Consent Review Gate
More screenshots
Works with the AI Agents you already use
OAuth Permission Expansion & Consent Review Gate
Compare two local OAuth app manifests and produce a fail-closed permission, publisher and redirect-URI expansion review before human consent.
$5
About this skill
Compare two local OAuth app manifests and produce a fail-closed permission, publisher and redirect-URI expansion review before human consent.
This downloadable local package turns authorized buyer-supplied files into a fixed, reproducible review packet. It includes an installable Python CLI, a local stdio MCP adapter and a companion Agent Skill.
Outputs
result.json, permission-delta.csv, redirect-uri-delta.csv, issues.jsonl, OAUTH_CONSENT_REVIEW.md and evidence-receipt.json
The core is deterministic, rejects unsafe paths and malformed inputs, never overwrites an existing packet, escapes formula-active CSV cells and binds each input and output with SHA-256. Processing stays local. No API key, login, upload, telemetry or live external action is included.
Best for
SaaS builders, IT administrators and security consultants reviewing OAuth app changes
Requirements
Windows 11 and Python 3.11–3.14; authorized local evidence files in the documented schemas; optional mcp==2.2.0 for the local MCP adapter.
Limitations
No tenant login, token inspection, publisher attestation, consent grant, revocation, malware detection, runtime behavior analysis or security certification. Demand and sales are not guaranteed; this is a one-time local V1.
No tenant login, token inspection, publisher attestation, consent grant, revocation, malware detection, runtime behavior analysis or security certification.
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 1 month ago
Requires
Permissions
Read buyer-selected authorized local input files and write a new review packet. Local shell execution for the Python CLI and optional local stdio MCP. No network, browser, account login or external actions.