Back to skill

Security audit

Short Video Script and Storyboard

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because scanners report capabilities and data collection beyond its stated script-and-storyboard purpose, along with risks involving broad shared credentials and persistent state.

The scanner verdict is suspicious, not malicious. Consider avoiding installation unless you are comfortable with the broader media-generation permissions, shared credential and cleanup risks, metadata reporting, and external processing of supplied photos. Scanning was marked partial: all 15 listed components were scanned, but some references in the skill instructions 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
  • 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 (34)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied code performs uninstall and authorization-lifecycle management, not scriptwriting or storyboard generation. Although uninstall tooling can legitimately accompany a skill, this chunk manages shared credentials and deletes persistent state—material capabilities not represented in the declared creative workflow. Its inventory checks, dry-run option, and conservative handling of other installed skills limit its effects but do not resolve the description-versus-behavior mismatch.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

Authorization and local credential storage can legitimately support remote image rendering, so those implementation details alone are not mismatches. However, the requested OAuth scope explicitly includes spending, audiovisual generation, and voice management beyond the declared script-and-stills workflow. The helper also requires the saved or issued scope to match this broad set exactly. This chunk obtains authorization for those capabilities; it does not itself demonstrate spending funds or generating media.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The reported automatic installation attribution and environment reporting are not necessary to produce scripts or storyboards and are not explained in the main workflow. Sending such metadata under a persistent installation identity introduces a limited privacy risk; the supplied source does not establish transmission of sensitive files or a complete local inventory.

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 50)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 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 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 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 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
86% confidence
Finding

The problem is not the credential filename but the explicit reuse of one full-scope bearer token across all packages without package-specific authorization. If one package or its client is compromised, that shared credential can expose capabilities beyond the package's intended task, increasing the blast radius; token secrecy instructions do not provide scope isolation.

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/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.

The manifest promises pre-production scripts and storyboard stills, but the workflow defaults to producing a finished audiovisual clip.

Medium
Category
Excessive Agency
Confidence
96% confidence
Finding

The manifest at L03 positions the skill as producing scripts and frames before filming or animation. In contrast, L18 makes clip production the default, and L37–L40 direct speech synthesis, music generation, shot animation, and final video composition—additional paid production operations rather than implementation details of storyboard rendering. The confirmation requirements mitigate unauthorized charges but do not resolve the advertised-scope mismatch.

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 script and storyboard generation.

Medium
Category
Excessive Agency
Confidence
96% confidence
Finding

The client automatically reports a stable installation reference alongside environment, network, provenance, and coarse runtime metadata, potentially every day, without a telemetry-specific choice described here. This reference discloses the behavior and excludes sensitive content, which limits severity, but persistent correlation remains unnecessary for the user's creative task.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
84% confidence
Finding

The documented update command uses an unpinned npx skills, which can download and execute a registry-selected CLI version with the caller's privileges. Although this is an update utility rather than an MCP server and is not automatically executed here, following the guidance introduces supply-chain exposure if a subsequently selected release is compromised.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
84% confidence
Finding

The second update example also invokes an unpinned npx skills, allowing the executable CLI version to change without review. This is the same supply-chain weakness in the global-install example, not evidence of a separate malicious MCP server.

Content

No source excerpt is available for this finding.

The workflow instructs uploading a product photo to media-generation services without a privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The workflow directs the agent to upload a product photo and pass it to image-generation and transformation tools, rather than merely listing available tools. It does not warn that user-provided media will be transmitted to an external service, which matters for private or unreleased product images.

Content

No source excerpt is available for this finding.

The workflow expands script-and-storyboard preparation into full audiovisual video production.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The manifest describes delivering a script and storyboard stills before filming or animation. In contrast, L29 directs speech and music generation, and L33–L35 require animating every shot and composing the clips with narration, music, and subtitles. These are additional production operations, not implementation details needed to produce scripts and storyboard frames.

Content

No source excerpt is available for this finding.