Shopify Product-Page Stills

• Outcome: Review
• Latest audit: Oct 21, 2026 · 4:43 AM UTC
• Version: 0.2.4

Overview

This image-making skill requires broader account access than it needs, and its uninstall logic can disconnect other Beatra skills.

Consider waiting for narrower account permissions and corrected uninstall checks. If installing, review the shared media and spending access, external image uploads, and automatic installation analytics. Approve live costs and check other Beatra skills before removal; access can be revoked in the Beatra Console.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Output Handling: Unvalidated Output Injection, Cross-Context Output, Unbounded Output
• Rogue Agent: Self-Modification, Session Persistence

Findings (33)

Description-Behavior Mismatch

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The supplied code does not process product facts, lay out themes, or generate Shopify images. Its purpose is uninstall-time management of a shared Beatra connection, including credential access, remote revocation, and conditional local-state deletion. These are substantive administrative capabilities not represented by the declared image-production purpose, rather than ordinary implementation details of creating images. The conservative inventory checks and dry-run option limit side effects but do not eliminate the description–behavior mismatch.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

Paid image generation reasonably requires spending authorization, and SKILL.md explicitly describes billing and approval, so wallet:spend is not inherently a purpose mismatch. However, the reported unrelated media permissions and persistent cross-package credential exceed this still-image workflow and increase the consequences of credential theft or misuse by another package. The authorization implementation was not supplied, so the excessive scope is supported by the static finding rather than independently verified here.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High

• Category: MCP Tool Poisoning
• Confidence: 96% confidence

Finding

The reported transmission of installation identity and runtime environment details for distribution analytics extends beyond generating product images and presents a privacy risk if performed without informed consent and data minimization. SKILL.md references registration but does not explain these analytics fields; the referenced documents and implementation were not supplied, limiting certainty about disclosure and collection. A generic remote-tool interface alone is not a vulnerability, although broad credentials could make unrestricted invocation more consequential.

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 53)May include surrounding context.

json

},
  "mcp": {
    "authentication": "device-bearer",
    "credential_file": "~/.beatra/credentials.json",
    "name": "beatra",
    "transport": "streamable-http",
    "url": "https://mcp.beatra.ai/mcp"

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.

md

- `~/.beatra/installation.json` contains one stable, non-secret installation
  reference.
- `~/.beatra/credentials.json` contains the single Device Token.

On POSIX systems the directory must be mode `0700` and both files mode `0600`.
On Windows the current user must be the only principal granted access through

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 53)May include surrounding context.

md

and keeps checking through brief network failures. One run waits up to
   about 15 minutes; an approval page stays open for up to an hour;
5. atomically saves the returned Device Token to
   `~/.beatra/credentials.json` without printing an HTTP response body;
6. validates the new credential with the same non-billable MCP request and
   prints `Beatra is ready` only after it succeeds.

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/updates-and-security.md (reported line 32)May include surrounding context.

md

These files are written under `~/.beatra/`. On POSIX that directory is mode
0700. Nothing is written inside the installed Skill directory.

- `credentials.json` (POSIX mode 0600), written by `scripts/authorize.py`: the device credential.
- `installation.json` (POSIX mode 0600), written by `scripts/authorize.py`: the stable installation reference.
- `host.json` (POSIX mode 0600), written by `scripts/authorize.py`: the agent environment, and a device name when one is known.
- `network.json` (POSIX mode 0600), written by `scripts/mcp_client.py`: this computer's network route.

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/updates-and-security.md (reported line 56)May include surrounding context.

md

When `scripts/uninstall.py` decides this is the last Beatra skill on the
computer, it first asks Beatra to revoke the device credential when one is
stored. If Beatra refuses, it changes nothing so the run can be repeated.
Otherwise it unlinks exactly these names in `~/.beatra/`: `credentials.json`,
`installation.json`, `host.json`, `skills.json`, `registrations.json`,
`network.json`, `balance-holds.json`, `pending_authorization.json`, and
`.authorize.lock`. It also unlinks `state.json`, `registration.json`, and

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 432)May include surrounding context.

python

def _existing_credential(state_dir: Path) -> Path | None:
    path = state_dir / "credentials.json"
    try:
        path_stat = os.lstat(path)
        if not stat.S_ISREG(path_stat.st_mode):

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.

md

the file ACL. Never copy the Device Token into conversation context, stdout,
stderr, a command argument, an environment variable, a log, a backup, a diff,
or another file. A completed authorization leaves the token only in
`~/.beatra/credentials.json`.

## Ensure Beatra is ready

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 42)May include surrounding context.

python

#: is empty — the script never recursively deletes a directory it does not
#: fully understand.
_STATE_FILES = (
    "credentials.json",
    "installation.json",
    "host.json",
    "skills.json",

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 12)May include surrounding context.

md

The host follows this computer's network route, described below.

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

Self-Modification

High

• Category: Rogue Agent
• Confidence: 90% confidence

Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · references/updates-and-security.md (reported line 3)May include surrounding context.

md

# Updates and security

Since the October 2026 releases, Beatra Skill packages contain no self-updater.
Earlier releases could replace their own files from Beatra's CDN; that code has
been removed. Updates now come only from the store or tool you installed the
Skill from.

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 1008)May include surrounding context.

python

scope = _required_string(polled, "scope")
    if set(scope.split()) != set(SCOPE.split()):
        raise RuntimeError("Beatra authorization returned an unsupported scope")
    credential_path = state_dir / "credentials.json"
    with _SIGNALS.deferred():
        _atomic_json(
            credential_path,

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 1183)May include surrounding context.

python

def _credentials(state_dir: Path) -> tuple[str, str]:
    state_dir = state_dir.expanduser()
    path = state_dir / "credentials.json"
    if not path.is_file():
        # Not connected yet (or the file is gone): the caller may still find
        # an approval waiting to be collected.

Malformed inventory entries are silently discarded, contradicting the documented fail-safe rule for shared credentials.

High

• Category: Excessive Agency
• Confidence: 98% confidence

Finding

The inventory loader silently drops every non-dictionary entry instead of treating the inventory as untrustworthy. If malformed entries represent other installed skills, uninstalling this package can incorrectly conclude that no skills remain, revoke the shared device credential, and delete shared state, disrupting those skills. The shared-connection context makes this more consequential than an ordinary package-local cleanup error.

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 · scripts/uninstall.py (reported line 132)May include surrounding context.

python

def _device_token(state_dir: Path) -> str | None:
    path = state_dir / "credentials.json"
    try:
        value = json.loads(path.read_text(encoding="utf-8"))
    except (OSError, ValueError):

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, file_read, file_write, network, shell.

Medium

• Category: MCP Least Privilege
• Confidence: 70% confidence

Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

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 106)May include surrounding context.

md

- say prominently that a signed-out browser lands on Beatra sign-in first:
  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 — never
  ask the user to confirm in chat that they approved.
- on the mainland China network, follow the sign-in and console-link guidance
  in [MCP connection](mcp-connection.md#network-route).

The authorization flow grants access to unrelated media capabilities beyond product-page image creation.

Medium

• Category: Excessive Agency
• Confidence: 92% confidence

Finding

The reference states that one approval grants access to image, video, music, speech, upload, model, and task tools, exceeding the image-generation needs of this Shopify skill. This least-privilege weakness increases the potential consequences of token theft or agent misuse, although the document does not establish the exact permissions or billing exposure.

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 132)May include surrounding context.

md

Use one of `website`, `github`, `skillhub`, `skillatlas`, `modelscope`,
`workbuddy`, `clawhub`, or `other`. If the conversation does not show it,
skip this and do not ask the user. If the command is not recognized, skip it.

## Use the bundled MCP client

Automatic installation telemetry is unrelated to generating Shopify product-page images.

Medium

• Category: Excessive Agency
• Confidence: 94% confidence

Finding

The documented behavior automatically transmits a stable installation reference, installation source, network-route information, and runtime metadata without describing explicit user consent. This enables installation tracking and environment profiling unrelated to generating Shopify product images; the stated exclusion of prompts, environment variables, and file paths limits the exposure but does not eliminate the privacy risk. The file documents this behavior rather than implementing it, so actual transmission and payload contents require verification in the bundled client.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium

• Category: MCP Rug Pull
• Confidence: 87% confidence

Finding

The documented npx skills update command does not pin the npm CLI version, so following it can download and execute a changing package with the caller's permissions. This is a conditional supply-chain exposure in optional maintenance guidance, not an MCP server configuration or evidence that the skill automatically executes the command.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium

• Category: MCP Rug Pull
• Confidence: 87% confidence

Finding

The second npx skills occurrence has the same unpinned CLI execution risk as the first: following the guidance can execute a newly resolved npm release with user privileges. These occurrences represent the same underlying maintenance-guidance issue, rather than two independent attack paths or an unpinned MCP server.

Content

No source excerpt is available for this finding.

The workflow instructs uploading seller-provided product or brand images without a privacy warning about external transmission.

Medium

• Category: Output Handling
• Confidence: 88% confidence

Finding

This is an instruction to upload seller-provided images, not merely a listing of an available tool. Although the upload mechanics are described, the workflow does not warn that the images will leave the local environment or identify the external service receiving potentially unpublished product or brand material.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.