Back to skill

Security audit

Bria Ai

Security checks across malware telemetry and agentic risk

Overview

This Bria image API skill does what it claims, with the main caution that it caches Bria credentials locally and sends selected images or prompts to Bria for processing.

Install only if you are comfortable connecting a Bria account, storing Bria tokens under ~/.bria/credentials, and sending chosen images, prompts, or image URLs to Bria's external service. Avoid confidential or regulated images unless Bria is approved for that data, restrict credential-file permissions after authentication, and delete or revoke cached credentials when no longer needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Lp3

Medium
Category
MCP Least Privilege
Confidence
96% confidence
Finding
The skill embeds executable shell workflows (`source`, credential parsing, and API helper invocation) but does not declare corresponding permissions. This creates a transparency and policy gap: an agent or user may invoke shell-capable behavior without an explicit permission boundary, increasing the chance of unexpected command execution and local file access. In this context the commands are operational rather than overtly malicious, but the undeclared capability still weakens trust and reviewability.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The skill instructs the agent to authenticate and cache tokens/API material in `~/.bria/credentials`, but the operational steps do not present a clear, prominent warning to the user about local credential persistence. Users may unknowingly leave reusable secrets on disk, which can later be accessed by other local processes, users, backups, or logs if file permissions are weak. The risk is elevated because the cached file contains both access-token and API-key material used for subsequent API calls.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
This reference makes clear that user images, prompts, and API credentials are sent to Bria's remote service, but it provides no privacy, consent, retention, or third-party data-sharing warning. In a skill that processes potentially sensitive user-provided images, this omission can cause unintentional disclosure of personal or proprietary content to an external vendor, especially if users assume processing is local.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The script stores access and refresh tokens in a predictable local file under ~/.bria/credentials without warning the user or enforcing restrictive permissions. If the file is readable by other local users, included in backups, or exfiltrated by other software, long-lived credentials could be reused to access the Bria account and API.

Session Persistence

Medium
Category
Rogue Agent
Content
name: bria-ai
description: >
  Bria.ai image API — generate from text prompts, edit with natural language,
  remove backgrounds for transparent PNGs, and create product lifestyle shots.
  Authenticates via OAuth device flow, caches credentials in ~/.bria/credentials,
  calls 20+ endpoints. Commercially safe, royalty-free.
  Triggers on: remove background, transparent PNG, cutout, generate image, create banner,
Confidence
92% confidence
Finding
create product lifestyle shots. Authenticates via OAuth device flow, caches credentials in ~/.bria/credentials, calls 20+ endpoints. Commercially safe, royalty-free. Triggers on: remove backgrou

Session Persistence

Medium
Category
Rogue Agent
Content
BRIA_ACCESS_TOKEN=$(printf '%s' "$TOKEN_RESPONSE" | sed -n 's/.*"access_token" *: *"\([^"]*\)".*/\1/p')
    if [ -n "$BRIA_ACCESS_TOKEN" ]; then
      REFRESH_TOKEN=$(printf '%s' "$TOKEN_RESPONSE" | sed -n 's/.*"refresh_token" *: *"\([^"]*\)".*/\1/p')
      mkdir -p ~/.bria
      printf 'access_token=%s\nrefresh_token=%s\n' "$BRIA_ACCESS_TOKEN" "$REFRESH_TOKEN" > "$HOME/.bria/credentials"
      echo "AUTHENTICATED"
      bria_introspect
Confidence
95% confidence
Finding
mkdir -p ~/.bria

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.