Back to skill

Security audit

music-generation-studio

Security checks for vulnerabilities and agentic risk

Overview

This music skill is not proven malicious, but it asks for broad account permissions and silently updates its own code, so users should review it before installing.

Install only if you are comfortable granting Beatra a broad shared device token that can spend account credits and access non-music media capabilities, and with the package silently updating itself by default. Consider disabling auto-updates with the documented command and reviewing Beatra account/device revocation controls before use.

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
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (4)

T05 · Unauthorized Access and Privilege Escalation

Error
Location
scripts/authorize.py:30
Finding

Overprivileged Shared Bearer Credential and Unrestricted MCP Tool Invocation

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 Skill is declared as a music-generation package, but its device authorization requests permissions for unrelated image, video, speech, and voice operations. It also requests broad `wallet:spend` authority. These permissions exceed the minimum capabilities required to generate music, upload relevant reference audio, and inspect or cancel associated tasks. The resulting bearer credential is stored in a shared `~/.beatra/credentials.json` file and may be reused by multiple Beatra Skills. This increases the impact of credential theft or misuse because compromise of one package can expose permissions granted for unrelated services. The generic `call` command accepts an arbitrary MCP tool name without applying a local allowlist. Consequently, possession ...[truncated 1552 chars]
Remediation
View remediation

other

Warning
Location
scripts/authorize.py:339
Finding

Unnecessary 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] ``` ```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 status, created = post_form(DEVICE_AUTHORIZATION_URL, form) ``` ### Technical Analysis The authorization h ...[truncated 2295 chars]
Remediation
View remediation

T03 · Remote Payload Retrieval and Execution

Error
Location
scripts/mcp_client.py:969
Finding

Silent Remote Package Replacement Without Publisher-Signature Verification

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 checked["update_available"]: return False _ensure_owned_baseline( insta ...[truncated 4095 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/mcp_client.py:241
Finding

Reference Audio Can Be Uploaded to Any MCP-Supplied HTTPS Host

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
Findings (35)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The referenced uninstall/removal workflow can read and modify local state under ~/.beatra, inspect installed package inventory, and revoke shared credentials, none of which is implied by the skill's music-creation description. These destructive or privacy-sensitive operations could affect other packages sharing the same connection state and therefore represent material hidden behavior.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The referenced uninstall/removal workflow can read and modify local state under ~/.beatra, inspect installed package inventory, and revoke shared credentials, none of which is implied by the skill's music-creation description. These destructive or privacy-sensitive operations could affect other packages sharing the same connection state and therefore represent material hidden behavior.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The referenced uninstall/removal workflow can read and modify local state under ~/.beatra, inspect installed package inventory, and revoke shared credentials, none of which is implied by the skill's music-creation description. These destructive or privacy-sensitive operations could affect other packages sharing the same connection state and therefore represent material hidden behavior.

Content

No source excerpt is available for this finding.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 79)May include surrounding context.

md
[music recipes](references/music-recipes.md) as patterns rather than fixed

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 162)May include surrounding context.

md
[music recipes](references/music-recipes.md) as patterns rather than fixed

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 request is far broader than this skill’s stated purpose of music generation. In addition to music generation, it requests artifact read/write, image/video generation, speech generation, voice read/write, task read/cancel, and wallet spending, creating unnecessary privilege if the credential is later abused or the skill is compromised.

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 actively provisions a shared credential with capabilities that exceed the manifest-level description of a music studio skill. This mismatch is dangerous because users may reasonably consent expecting music-only behavior while the resulting token can perform broader multimodal and spending actions.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file implements a full self-update system that fetches discovery metadata, manifests, and archives from remote infrastructure and then overwrites installed package files. Even with checksum and path validation, this materially expands the trust boundary for a music-generation skill: compromise of the vendor update channel, signing/distribution pipeline, or update origin lets remote code change local behavior outside the user’s immediate review.

Content

No source excerpt is available for this finding.

Self-Modification

High
Category
Rogue Agent
Confidence
95% confidence
Finding

The skill explicitly exposes self-update functionality that can modify its own installed code. Self-modification is especially risky for a music-generation skill because it is unrelated to the declared purpose and gives remote infrastructure a direct path to alter future execution semantics on the host.

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
90% confidence
Finding

The skill text directs use of shell, network, file upload, and local client operations, but it declares no explicit tool scope or permissions boundaries. That makes the effective capability set broader and less transparent than the metadata suggests, increasing the risk of unintended file, network, or command execution in environments that honor declared scopes.

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 · SKILL.md (reported line 3)May include surrounding context.

md
---
name: "music-generation-studio"
description: "Create original songs, AI-generated music, lyrics-to-song tracks, instrumentals, background music, video soundtracks, jingles, multilingual songs, and reference-led arrangements from a clear creative brief. This AI music generator and AI song maker develops genre, mood, structure, singable lyrics, vocal direction, and production style, then creates reviewable audio with Suno 5.5 or another model you explicitly choose. Use it as an AI music studio for songwriting, an AI lyrics writer, text-to-music creation, BGM generation, brand music, podcast themes, game music, bilingual songs, or focused new versions of reference audio. Review vocals, pronunciation, duration, loop points, and arrangement fit after generation, then refine the strongest result."
---

# Music Generation Studio

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
---
name: "music-generation-studio"
description: "Create original songs, AI-generated music, lyrics-to-song tracks, instrumentals, background music, video soundtracks, jingles, multilingual songs, and reference-led arrangements from a clear creative brief. This AI music generator and AI song maker develops genre, mood, structure, singable lyrics, vocal direction, and production style, then creates reviewable audio with Suno 5.5 or another model you explicitly choose. Use it as an AI music studio for songwriting, an AI lyrics writer, text-to-music creation, BGM generation, brand music, podcast themes, game music, bilingual songs, or focused new versions of reference audio. Review vocals, pronunciation, duration, loop points, and arrangement fit after generation, then refine the strongest result."
---

# Music Generation Studio

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill explicitly allows the bundled client to auto-check for and install higher package versions without separate confirmation during ordinary command execution. Even with claimed verification, silent self-update is a supply-chain and consent risk because the executed code can change over time without an immediate user decision at the point of use.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The document states that the client silently checks for and automatically installs newer releases by default without separate confirmation. Even with integrity checks, unattended self-updating code that replaces installed files expands the trust boundary and can lead to unexpected code execution or system modification if the update channel, signing process, or release pipeline is ever compromised.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

These lines direct the brief to include language, region, and script choices as part of the default template. That can steer outputs toward a specific language or locale even when the user has not explicitly asked for one, which conflicts with the policy against forcing language or locale without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.