A transparent proxy for the Facebook Graph API. Replace the domain, pass your Yuri API token, and call any Facebook endpoint — no Facebook access token needed on the client side.

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This is a disclosed Facebook API proxy, but it routes broad Facebook account authority and data through a third-party gateway that supports all endpoints, including write and delete actions.

Use this only if you trust baiz.ai to handle Facebook account authority and request data. Start with a test or least-privilege account, avoid production Facebook assets, require human confirmation for any write/delete/publish/ad-management action, and verify token scopes, logging, retention, and revocation before installing or using it.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

#
ASI03: Identity and Privilege Abuse
High
What this means

The provider and anyone with the Yuri token may be able to act on linked Facebook resources, potentially affecting pages, ads, business assets, or account data.

Why it was flagged

The guide requires delegating Facebook authorization to a third-party service or using a pre-authorized Facebook account supplied by that service.

Skill content
Choose one: ... "Request access" | Contact the Yuri team to get a pre-authorized Facebook account ... "Authorize your own" | Link your Facebook account through the Yuri dashboard
Recommendation

Use only test or least-privilege Facebook assets until the provider is verified; confirm OAuth scopes, revocation, audit logs, and who can access any pre-authorized accounts.

#
ASI02: Tool Misuse and Exploitation
High
What this means

An agent using this skill could make high-impact Facebook API calls, including edits, deletes, uploads, or public/business changes, if given a valid token.

Why it was flagged

The skill exposes the full raw Facebook Graph API through the proxy, including mutating and deleting operations, with no documented guardrails or approval workflow.

Skill content
HTTP methods | GET, POST, PUT, DELETE, etc. ... Endpoints | All Facebook Graph API endpoints and versions ... File uploads | multipart/form-data
Recommendation

Require explicit user confirmation for POST, PUT, DELETE, uploads, publishing, ad changes, or account-management actions, and prefer narrowly scoped tokens and endpoint allowlists.

#
ASI07: Insecure Inter-Agent Communication
Medium
What this means

Facebook request data and account-related operations may be visible to or processed by the gateway provider, including potentially sensitive business or user data.

Why it was flagged

All Facebook API paths, parameters, bodies, uploads, and token resolution are routed through the external baiz.ai gateway, but the artifacts do not describe retention, logging, isolation, or data-use limits.

Skill content
Replace graph.facebook.com with facebook-graph.baiz.ai ... Everything else — paths, query parameters, request bodies, HTTP methods — stays identical ... Facebook access tokens are securely stored and managed on the server.
Recommendation

Review the provider’s privacy, retention, logging, and security documentation before use; avoid sensitive uploads or production data until those controls are verified.

#
ASI04: Agentic Supply Chain Vulnerabilities
Low
What this means

The static scan being clean only means there was no local code to analyze; it does not verify how the external proxy stores tokens or handles Facebook requests.

Why it was flagged

There is no local code to inspect, and the real security properties depend on an external gateway whose implementation is not included in the artifact set.

Skill content
Source: unknown ... No code files present — this is an instruction-only skill.
Recommendation

Treat the provider as part of the trusted computing base and verify its documentation, ownership, audit status, and support for token revocation before relying on it.