Back to skill

Security audit

AI Image Generation Studio

Security checks for vulnerabilities and agentic risk

Overview

The skill performs the advertised image workflow, but it also uses a broad shared Beatra authorization and silent self-updates that deserve careful review before installation.

Review this before installing in sensitive environments. Only install if you are comfortable with a shared Beatra device token that can cover non-image media and wallet-backed operations, with local hostname/platform registration, and with default silent package updates. Consider disabling auto-updates with the documented update --auto off command and revoking the device from the Beatra Console when no longer needed.

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (3)

T05 · Unauthorized Access and Privilege Escalation

Error
Location
scripts/authorize.py:31
Finding

Image-Only Skill Requests and Can Exercise Excessive Cross-Media Permissions

Content
View full analysis
dict[str, Any]: session = _session_with_registration( state_dir=Path.home() / ".beatra", post_json=_default_post_json, ) if command == "tools": return session.request(2, "tools/list", {}) try: arguments = json.load(os.sys.stdin) except json.JSONDecodeError as exc: raise RuntimeError("Tool arguments on stdin must be one JSON object") from exc if not isinstance(arguments, dict): raise RuntimeError("Tool arguments on stdin must be one JSON object") assert tool_name is not None return session.request( 2, "tools/call", {"name": tool_name, "arguments": arguments}, ) ``` ### Technical Analysis The declared functionality is image generation, image transformation, and image editing. The requested bearer-token scope additionally permits video, music, speech, and voice operations, artifact and task reads, task cancellation, and wallet spending. These permissions exceed the minimum privileges required by the Skill. The issue is operationally significant because the bundled client does not restrict `call` to image-related tools. It forwards an arbitrary caller-supplied tool name and JSON arguments to the remote MCP endpoint using the broadly scoped bearer credential. Although the documentation discloses that one authorization covers multiple media ...[truncated 1290 chars]
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
scripts/authorize.py:340
Finding

Authorization Collects and Transmits Hostname and Agent-Environment Telemetry

Content
View full analysis
str: """The agent environment this process runs inside (docs/device-model.md). Order: explicit agent self-report > environment signatures > unknown. Detection reads the process environment only — nothing else runs, nothing reaches the network. """ if explicit: candidate = explicit.strip().lower().replace(" ", "-") if _PLATFORM_VALUE.fullmatch(candidate): return candidate env = os.environ if env.get("CLAUDECODE") == "1" or "CLAUDE_CODE_ENTRYPOINT" in env: return "claude-code" if any(key.startswith("CODEX_") for key in env): return "codex" ai_agent = env.get("AI_AGENT", "").lower() matched = re.match(r"([a-z0-9-]+)_", ai_agent) if matched and _PLATFORM_VALUE.fullmatch(matched.group(1)): return matched.group(1) return "unknown" def device_display_name() -> str | None: """A hostname the user will recognise in the console device list.""" try: name = socket.gethostname().strip() except OSError: return None if not name or not name.isprintable(): return None return name[:120] ``` The collected values are included in the authorization request: ```python form: dict[str, str] = { "client_id": CLIENT_ID, "resource": MCP_URL, "scope": SCOPE, "platform": host_platform, "client_name": PACKAGE_DISPLAY_NAME, "external_installation_ref": external_reference, "package_version": PACKAGE_VERSION, "package_slug": PACKAGE_SLUG, } if device_name: form["device_name"] = device_name ``` Platform and package attribution are al ...[truncated 2433 chars]
Remediation
View remediation

T03 · Remote Payload Retrieval and Execution

Error
Location
scripts/mcp_client.py:969
Finding

Default Silent Updater Retrieves and Replaces Executable Skill Code

Content
View full analysis
bool: """Best-effort silent update. Never block the requested MCP command.""" resolved_state = state_dir or Path.home() / ".beatra" try: resolved_root = (install_root or _current_install_root()).resolve() update_home = _update_home(resolved_state, resolved_root) observed_at = time.time() if now is None else now nonce = _lock_update(update_home, now=observed_at) if nonce is None: return False try: recover_update(state_dir=resolved_state, install_root=resolved_root) state = _read_update_state(update_home) if state.get("auto_update", True) is False: return False last_checked = state.get("last_checked_at") if ( isinstance(last_checked, (int, float)) and observed_at - float(last_checked) < UPDATE_CHECK_MAX_AGE_SECONDS ): return False state["last_checked_at"] = observed_at _write_private_json(update_home / "state.json", state) checked = check_update(get_bytes=get_bytes) if not checke ...[truncated 3811 chars]
Remediation
View remediation
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (29)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The referenced behaviors include uninstall logic, reading shared installation inventory, deleting credential/state files, revoking tokens, and managing shared connection lifecycle, none of which are apparent from the advertised image-editing purpose. In context, that means the skill can affect broader host account and installation state, so misuse or compromise would have consequences beyond a single image task.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The referenced behaviors include uninstall logic, reading shared installation inventory, deleting credential/state files, revoking tokens, and managing shared connection lifecycle, none of which are apparent from the advertised image-editing purpose. In context, that means the skill can affect broader host account and installation state, so misuse or compromise would have consequences beyond a single image task.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The referenced behaviors include uninstall logic, reading shared installation inventory, deleting credential/state files, revoking tokens, and managing shared connection lifecycle, none of which are apparent from the advertised image-editing purpose. In context, that means the skill can affect broader host account and installation state, so misuse or compromise would have consequences beyond a single image task.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · manifest.json (reported line 71)May include surrounding context.

json
```

They share the one full-scope Device Token stored in
`~/.beatra/credentials.json`. Installing or switching packages must not trigger
another authorization when that credential is already valid. Do not add,
enable, trust, or configure a host Beatra Connector. Never print or move the
token into command arguments, environment variables, logs, chat, or another

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/installation-and-auth.md (reported line 14)May include surrounding context.

text

They share the one full-scope Device Token stored in
`~/.beatra/credentials.json`. Installing or switching packages must not trigger
another authorization when that credential is already valid. Do not add,
enable, trust, or configure a host Beatra Connector. Never print or move the
token into command arguments, environment variables, logs, chat, or another

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/installation-and-auth.md (reported line 21)May include surrounding context.

text

They share the one full-scope Device Token stored in
`~/.beatra/credentials.json`. Installing or switching packages must not trigger
another authorization when that credential is already valid. Do not add,
enable, trust, or configure a host Beatra Connector. Never print or move the
token into command arguments, environment variables, logs, chat, or another

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/installation-and-auth.md (reported line 49)May include surrounding context.

text

They share the one full-scope Device Token stored in
`~/.beatra/credentials.json`. Installing or switching packages must not trigger
another authorization when that credential is already valid. Do not add,
enable, trust, or configure a host Beatra Connector. Never print or move the
token into command arguments, environment variables, logs, chat, or another

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/mcp-connection.md (reported line 10)May include surrounding context.

text

They share the one full-scope Device Token stored in
`~/.beatra/credentials.json`. Installing or switching packages must not trigger
another authorization when that credential is already valid. Do not add,
enable, trust, or configure a host Beatra Connector. Never print or move the
token into command arguments, environment variables, logs, chat, or another

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/authorize.py (reported line 207)May include surrounding context.

python
```

They share the one full-scope Device Token stored in
`~/.beatra/credentials.json`. Installing or switching packages must not trigger
another authorization when that credential is already valid. Do not add,
enable, trust, or configure a host Beatra Connector. Never print or move the
token into command arguments, environment variables, logs, chat, or another

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/authorize.py (reported line 514)May include surrounding context.

python
```

They share the one full-scope Device Token stored in
`~/.beatra/credentials.json`. Installing or switching packages must not trigger
another authorization when that credential is already valid. Do not add,
enable, trust, or configure a host Beatra Connector. Never print or move the
token into command arguments, environment variables, logs, chat, or another

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/mcp_client.py (reported line 1025)May include surrounding context.

python
```

They share the one full-scope Device Token stored in
`~/.beatra/credentials.json`. Installing or switching packages must not trigger
another authorization when that credential is already valid. Do not add,
enable, trust, or configure a host Beatra Connector. Never print or move the
token into command arguments, environment variables, logs, chat, or another

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/uninstall.py (reported line 40)May include surrounding context.

python
```

They share the one full-scope Device Token stored in
`~/.beatra/credentials.json`. Installing or switching packages must not trigger
another authorization when that credential is already valid. Do not add,
enable, trust, or configure a host Beatra Connector. Never print or move the
token into command arguments, environment variables, logs, chat, or another

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/uninstall.py (reported line 109)May include surrounding context.

python
```

They share the one full-scope Device Token stored in
`~/.beatra/credentials.json`. Installing or switching packages must not trigger
another authorization when that credential is already valid. Do not add,
enable, trust, or configure a host Beatra Connector. Never print or move the
token into command arguments, environment variables, logs, chat, or another

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The OAuth scope requested by this image-generation skill includes many capabilities unrelated to its stated purpose, such as wallet spending, task control, artifact access, and generation of videos, music, speech, and voice operations. This violates least privilege and means that if the credential is compromised or the skill is abused, an attacker gains far broader access than users would reasonably expect from an image-focused package.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The authorization flow provisions a shared credential for an image-focused skill, but the code hardcodes a broad scope set far beyond image operations. In context, this mismatch is especially concerning because users installing a narrowly described creative tool would not expect to authorize wallet spending or non-image media generation, increasing the chance of deceptive over-authorization and downstream abuse.

Content

No source excerpt is available for this finding.

Self-Modification

High
Category
Rogue Agent
Confidence
91% confidence
Finding

The package exposes explicit self-update functionality and also supports automatic in-place modification of its own installed files. In a skill whose stated role is image generation/editing, self-modification is especially dangerous because it expands trust from content generation to code lifecycle control, enabling future behavior changes without the narrow scope users expect.

Content

Scanner excerpt · scripts/mcp_client.py (reported line 1503)May include surrounding context.

python
)
    update = subparsers.add_parser(
        "update",
        help="Check, install, or configure Beatra package self-updates",
    )
    update.add_argument(
        "--check",

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill declares no explicit tool/permission scope even though its instructions require shell, file, network, and environment access. That creates an over-privileged execution surface where a host may grant broad capabilities by default, increasing the chance of unintended file access, command execution, or network operations beyond image-generation needs.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill states that its bundled client silently checks for and installs newer releases without separate confirmation. Even with integrity checks, auto-replacing executable package files creates a supply-chain risk: future behavior can change after review, and a compromised update channel or signing process would let new code run under the skill's existing trust and permissions.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · manifest.json (reported line 9)May include surrounding context.

json
"icon": "https://beatra.ai/textures/icons/ai-image-generation-studio-0.1.1.png",
  "localized": {
    "en": {
      "description": "Create and refine images from a written brief, one to four ordered reference images, or an existing base image. AI Image Generation Studio supports text-to-image generation, reference-guided composition, and focused AI image editing for product photos, ad creative, brand visuals, posters, social graphics, illustrations, concept art, and photo background changes. Review each generated image for message, subject fidelity, composition, style, text, and destination fit, then choose the smallest useful edit, new composition, or new generation.",
      "display_name": "AI Image Generation Studio",
      "summary": "Generate, compose, and edit product images, brand visuals, posters, social graphics, illustrations, and photo variations.",
      "tags": [

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The document states that silent update checks and automatic installation are enabled by default and occur before ordinary commands, which means local files may be modified without an explicit, prominent warning at point of use. Even with integrity checks and rollback, default-on self-updating increases supply-chain and change-management risk because users may not realize the tool can alter the local installation automatically.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/installation-and-auth.md (reported line 64)May include surrounding context.

md
the user signs in or creates their account there, and the approval page
  continues automatically after sign-in;
- say once that the connection continues automatically after Allow, then
  detect completion yourself — never ask the user to confirm in chat that
  they approved.

Approval legitimately takes minutes when sign-in or account creation is

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file fixes the package locale to 'en', and that value is later enforced in update and manifest validation logic. This appears to force a specific language/locale without any user opt-in or documented choice mechanism, which matches the language/locale policy violation category.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This client for an image-generation skill contains extensive package-management and self-update logic unrelated to the declared creative purpose. In the skill context, that scope expansion is risky because it gives the package the ability to fetch, validate, and replace local installation files, increasing attack surface and enabling code changes beyond what a user would expect from an image tool.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

maybe_auto_update() performs silent, best-effort self-update of package files during ordinary command execution, without a user-facing warning at the point of action. Even though the code includes integrity checks, silent code replacement is dangerous in this skill context because it changes executable behavior unexpectedly and turns normal use of an image tool into an implicit software-modification event.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The code records local skill inventory and sends installation telemetry, neither of which is necessary for core image-generation behavior described in the skill metadata. In this context, undisclosed device inventory and telemetry collection create privacy and governance risk because users invoking an image tool would not reasonably expect local tracking and registration side effects.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.