Back to skill

Security audit

product-video-studio

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this product video skill suspicious because scanners report broad account access, persistent installation tracking, and other capabilities that exceed its stated video-making purpose.

Consider the verdict suspicious before installing. Review whether you are comfortable with a shared, persistent account credential, its reported broad permissions, automatic installation and environment reporting, and the possibility that product images or narration are sent to Beatra without a clear disclosure. The scan was partial: all listed components were inspected, but some local references could not be resolved, so the evidence is incomplete.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (38)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

Installation registration sends persistent attribution and runtime metadata that are unnecessary for generating a product video. Although a linked reference documents this reporting, automatic collection without a prominent notice or documented opt-out creates a limited privacy and correlation risk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The supplied code performs lifecycle and authorization cleanup, not photo processing, scriptwriting, narration, or video generation. Although uninstall tooling can legitimately accompany a skill, revoking shared device authorization and deleting shared state are substantial capabilities not disclosed by the declared video-generation purpose. The code includes conservative checks and a dry-run mode; the mismatch does not itself establish malicious behavior.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The shared, persistent, full-scope authorization described in the packet gives this workflow a broader account-access boundary than its product-video purpose requires. Spending is explicitly disclosed and confirmation-gated, so that portion of the mismatch is overstated; the unnecessary cross-package authorization remains a least-privilege concern.

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
},
  "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 · scripts/authorize.py (reported line 436)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 · scripts/authorize.py (reported line 1012)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.

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
95% confidence
Finding

The concern is not the credential filename but the explicit reuse of one full-scope token across all skill packages without renewed authorization. A compromised or overreaching package can consequently exercise broader account privileges than its individual workflow needs, increasing the blast radius.

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 · 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/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.

Unbounded Output

Medium
Category
Output Handling
Confidence
60% confidence
Finding

Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Content

Scanner excerpt · references/copy-craft.md (reported line 19)May include surrounding context.

md
## Length is a budget — verify it free with `beatra.speech.validate` before paying

The finished video runs at most 15 seconds, and the video cannot be shorter than the narration without cutting the last words off. Always write to about **12 seconds** first (roughly 55 to 60 Simplified Chinese characters, or a little over one English sentence), leaving a three-second reserve so the cut lands cleanly.

When pacing, pauses, dramatic emphasis, or pronunciation notes would help the read, call **`beatra.speech.prepare_script`** (Smart Voice Director, after `{"capability": "speech_script"}`, listed as its own paid line when run; never alters the merchant's approved wording; re-calling `prepare_script` within 48 hours with the same script and instructions when changing only `voice`/`model` charges zero credits; max 2 concurrent). Never hand-author braced markup or strip `/` slashes manually.

The workflow sends merchant narration to Beatra speech services without a privacy disclosure.

Medium
Category
Output Handling
Confidence
87% confidence
Finding

These steps instruct the agent to submit the narration to Beatra for script preparation, validation, and synthesis. Although charges are explained, the file does not warn that the script, including merchant-supplied product or offer details, will be transmitted to a third-party service.

Content

No source excerpt is available for this finding.

The workflow sends merchant images to an image-processing service without a privacy disclosure.

Medium
Category
Output Handling
Confidence
89% confidence
Finding

The skill instructs the agent to submit the merchant's photo to beatra.images.transform; line 54 also directs submission of the accepted frame to beatra.images.edit. Although it warns about paid calls and visual changes, it does not tell the merchant that their image will be sent to an external service for processing.

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 120)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).

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 146)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 product-video generation.

Medium
Category
Excessive Agency
Confidence
95% confidence
Finding

Automatic registration associates a stable installation reference with runtime, distribution, and network metadata, potentially repeatedly. The reference discloses the behavior and excludes content and secrets, reducing severity, but provides no documented consent or opt-out mechanism for nonessential reporting.

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/speech-and-audio.md (reported line 46)May include surrounding context.

md
Before starting any paid speech, dialogue, cloning, conversion, transcription, SFX, or finishing task:

1. Run any applicable free preflight (`beatra.voices.list` / `beatra.voices.preview` / `beatra.speech.validate` / `beatra.speech.validate_dialogue`) and read live rates via `beatra.models.list`. Keep `beatra.wallet.get` and `beatra.wallet.ledger` as optional read-only tools for answering balance or charge questions — never make `beatra.wallet.get` a mandatory gate before submit, and never ask the user to confirm they have enough credits.
2. Present a concise confirmation summarizing the **six required fields** before the first paid step (after all inputs and parameters are settled):
   - **Work**: exact capability, voice choice, language/duration/format, and any planned finishing step.
   - **Credits**: quoted credits from `beatra.models.list` / preflight (never guess or hardcode prices).

The workflow sends user scripts and contextual text to Beatra without a privacy or external-processing disclosure.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The workflow sends spoken copy and optional surrounding context to an external service without requiring a user-facing explanation of that transfer. Approval of a paid narration operation does not necessarily establish informed permission to disclose confidential launch copy or additional contextual text.

Content

No source excerpt is available for this finding.