Security audit

Firebase Auth Setup

Security checks for vulnerabilities and agentic risk

Overview

The skill is broadly an auth setup helper, but it under-discloses a privileged Firebase-to-Supabase profile sync that handles user identity data and service-role database access.

Install only if you intentionally want Firebase logins mirrored into Supabase profiles. Keep FIREBASE_PRIVATE_KEY and SUPABASE_SERVICE_ROLE_KEY server-only, ask for an explicit sync opt-in, add rate limiting and generic error responses, and limit writes to the minimum profile fields needed.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (2)

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:239
Finding: Raw Backend Error Disclosure in Authentication Sync Endpoint Template
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Note

Location: SKILL.md:214
Finding: Authentication Sync Endpoint Template Does Not Enforce Rate Limiting
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill is presented as Firebase Authentication setup, but it also instructs the agent to provision a Supabase profile-sync pipeline and perform database writes. That scope expansion matters because it can cause the agent to introduce cross-system data flows and persistence changes the user may not have intended, increasing the chance of privacy, integrity, and least-privilege violations.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The sync flow sends Firebase-derived identity attributes such as UID, email, name, and avatar to Supabase, but the skill description does not clearly warn users about this data transfer. That omission is risky because users may invoke a seemingly auth-only setup skill without realizing it establishes a new identity replication path and additional data processing surface.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The documented implementation creates a Supabase client with SUPABASE_SERVICE_ROLE_KEY, giving the route broad administrative write capability that bypasses RLS. In a skill ostensibly focused on Firebase auth setup, embedding privileged cross-system database access is dangerous because any misuse, route abuse, or future code change could modify protected data well beyond the minimum required auth function.
Content: No source excerpt is available for this finding.

Scope Creep

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The manifest advertises only filesystem permission, but the runtime requirements ask for numerous sensitive environment variables, including Firebase private key material and a Supabase service-role key. This creates a transparency and trust problem: users may underestimate the skill's effective access to secrets, making secret exposure or misuse more likely in an agentic environment.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill is for Firebase Authentication setup, but it also requests Supabase secrets including SUPABASE_SERVICE_ROLE_KEY, a highly privileged server-side credential unrelated to the stated purpose. Unnecessary declaration of unrelated secrets expands the blast radius: if the skill, its prompts, or downstream code mishandle environment variables, an attacker could gain full administrative access to Supabase resources.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: Line L017 instructs the agent not to read .env.local or any file containing actual credential values. Later, the skill's code examples depend on process.env.SUPABASE_SERVICE_ROLE_KEY and other secret-backed runtime configuration, creating tension between the stated handling of credentials and the implementation guidance.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.