Back to skill

Security audit

Beatra AI Voice Studio

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious with medium confidence because scanners report capabilities and permissions beyond its stated voice-generation purpose, automatic installation and runtime analytics, and an uninstall edge case that could affect shared authorization.

Consider avoiding installation unless you need the broader reported capabilities and accept automatic analytics without a described opt-out. The review is suspicious, not a claim of malicious intent. Evidence is incomplete: Skillspector marked its analysis partial because some references could not be resolved and binary image content was outside analyzer coverage; the separate AIG scan completed with no findings.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Rogue AgentSelf-Modification, Session Persistence
Findings (39)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supporting documentation describes a shared full-scope credential covering image, video, and music operations, although this skill explicitly confines itself to voice and audio workflows. Such excess authority increases the consequences of credential theft or agent misuse; spending authority itself is expected for the disclosed paid audio operations and is not independently evidence of a mismatch.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

Automatic installation reporting links a persistent installation identifier with runtime and distribution information, while source attribution accompanies tool calls. Although references disclose this behavior, it is not necessary for voice generation and operates without a documented user choice, creating a privacy and data-minimization concern rather than evidence of malicious exfiltration.

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 76)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 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 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
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 · 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 · 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
75% 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 · SKILL.md (reported line 112)May include surrounding context.

md
synthesis call; show the six-field production card (Route & Model,
     Exact Scope, Price & Basis, Duration / Quantity,
     Pay Mode & Call Count, and If stop detailing free deliverables kept
     at zero extra charge) alongside the delivery without asking twice.
   - Obtain explicit approval on the six-field card BEFORE calling
     `prepare_script`, `synthesize_dialogue`, `speech.convert`, `voices.clone`,
     `voices.activate`, `voices.delete`, `audio.transcribe`, `audio.generate_sfx`,

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 · SKILL.md (reported line 201)May include surrounding context.

md
speech estimates via `estimate_formula`, `unit_price_credits`, `scale`, and
`billing_basis: "beatra_weighted_characters"` (Han = 2, others = 1).

Never make `beatra.wallet.get` a mandatory gate before paid submission and never
ask users to confirm they have enough credits. Call read-only `beatra.wallet.get`
when asked about balance/fit and `beatra.wallet.ledger` when asked what was
charged; relay `top_up` tiers in returned order verbatim. On

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/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).

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 analytics are unrelated to the declared voice-generation purpose.

Medium
Category
Excessive Agency
Confidence
94% confidence
Finding

The client automatically reports a stable installation reference alongside host, runtime, locale, network, and distribution metadata, potentially every day. Documentation and a privacy-policy reference provide some transparency, but no user control is described, allowing persistent analytics beyond what audio production requires.

Content

No source excerpt is available for this finding.

The skill expands from TTS, narration, and voice cloning into transcription, sound-effect generation, and stem separation.

Medium
Category
Excessive Agency
Confidence
90% confidence
Finding

The manifest describes generating narration from supplied text and creating reusable cloned voices. L43–L45 instead authorize paid transcription, sound-effect generation, and stem separation, with L17 explicitly routing these workflows into this skill; these are distinct audio-production capabilities rather than necessary implementation details of the declared purpose.

Content

No source excerpt is available for this finding.

The workflow sends user scripts and contextual text to Beatra without a privacy disclosure.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

These workflow steps explicitly instruct the agent to pass the customer's spoken copy, delivery instructions, and optional surrounding context to Beatra's script-preparation service. Although the guide requires confirmation of costs and work parameters, it never requires disclosure that potentially sensitive text or recordings will be sent to an external service.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
86% confidence
Finding

The documented update command invokes an unpinned npm executable through npx, which can fetch and execute a changing package version with the caller's privileges. This is a supply-chain exposure rather than an unpinned MCP server; its optional, manually invoked update context limits immediate exposure.

Content

No source excerpt is available for this finding.