Radio Drama Ad Breaks

• Outcome: Review
• Latest audit: Oct 21, 2026 · 4:42 AM UTC
• Version: 0.2.4

Overview

This audio skill needs review because it requires unrelated account permissions and its uninstall checks can wrongly disconnect other Beatra skills.

Ask the publisher for speech-only authorization and corrected uninstall checks before granting access. Consider the recurring device analytics and shared credential, approve paid work explicitly, and use Beatra Console to revoke device access when needed.

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
• Rogue Agent: Self-Modification, Session Persistence
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration

Findings (33)

Description-Behavior Mismatch

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence

Finding

The supplied chunk contains no speech synthesis, bumper-slot processing, or audio-file delivery. Its primary behavior is uninstalling a skill's shared connection state, including credential access, a network revocation request, and local file deletion. Although an uninstaller can legitimately accompany an audio skill, these materially distinct administrative capabilities are not represented by the declared description. The code includes safeguards to preserve connections used by other skills, but those safeguards 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: 98% confidence

Finding

The reported authorization for image, video, and music generation exceeds the spoken-bumper workflow, and a broadly scoped credential shared across packages would increase the consequences of credential theft or misuse by another package. Spending, voice creation, and task cancellation are justified by the documented workflow, but unrelated generation privileges are not; the underlying authorization implementation was not supplied, so this assessment relies on the static report.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High

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

Finding

Authentication, remote transport, routing, billing safeguards, and version notices can reasonably support a hosted audio skill and are not independently grounds for a mismatch. However, this client also performs installation analytics reporting, including OS/version, architecture, Python version, locale, and timezone offset, which the description does not disclose. Its upload and tool-call interfaces are substantially broader than the stated workflow. The supplied chunk may support audio generation elsewhere, but it neither establishes nor enforces the promised one-clip-per-slot, 8–20-file behavior. The mismatch rests primarily on the additional reporting and broad exposed capabilities, not merely on the absence of synthesis logic in a helper file.

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 52)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/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 · 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 · 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.

Authorization requests unrelated media-generation and voice-management capabilities.

High

• Category: Excessive Agency
• Confidence: 99% confidence

Finding

A skill that produces spoken bumper clips requests image, video, and music generation plus voice-management privileges beyond its stated purpose. The helper also requires the complete scope set when accepting credentials, preventing narrower authorization; misuse or compromise of the resulting token could therefore enable unrelated operations and consume account resources.

Content

No source excerpt is available for this finding.

Malformed inventory entries are silently discarded, allowing shared credential revocation despite the documented fail-safe policy.

High

• Category: Excessive Agency
• Confidence: 98% confidence

Finding

The inventory loader silently drops non-dictionary entries instead of treating the inventory as unreliable. An inventory containing malformed records can therefore appear to contain no other installed skills, allowing uninstall to revoke the shared credential and delete shared state, disrupting otherwise installed skills. This is particularly consequential because the uninstaller manages a connection shared beyond the radio-drama skill.

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).

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

The skill documents automatic installation telemetry unrelated to producing radio-drama bumper clips.

Medium

• Category: Excessive Agency
• Confidence: 96% confidence

Finding

The document describes automatic, recurring transmission of a stable installation reference alongside installation-source, network-route, and runtime metadata, without describing user consent or a way to disable reporting. This creates a privacy risk through persistent installation tracking and metadata collection unrelated to producing bumper audio. The disclosed purpose and stated exclusions reduce suspicion of malicious intent, but the document alone does not verify those exclusions or establish adequate consent.

Content

No source excerpt is available for this finding.

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

Medium

• Category: MCP Rug Pull
• Confidence: 83% confidence

Finding

Although this is an update CLI rather than an MCP server, the documented npx skills command can download and execute an unpinned npm package with the caller's privileges. A compromised package release could therefore execute arbitrary code if the command is followed; the exposure is limited to an explicitly initiated maintenance action, not ordinary audio generation.

Content

No source excerpt is available for this finding.

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

Medium

• Category: MCP Rug Pull
• Confidence: 83% confidence

Finding

The second npx skills occurrence has the same unpinned package-execution risk as the first; it is another invocation form, not an independent vulnerability. The global-update variant also requests changes to globally installed skills, although compromise of the invoked CLI would already permit actions within the caller's permissions.

Content

No source excerpt is available for this finding.

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

Medium

• Category: MCP Rug Pull
• Confidence: 70% confidence

Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.