REDnote Note Copywriter

• Outcome: Review
• Latest audit: Oct 21, 2026 · 4:58 AM UTC
• Version: 0.2.4

Overview

This writing skill requires broader account permissions than its task needs, including spending and media controls.

Review the Beatra approval carefully: free text drafting still requests spending and account-changing permissions. Prefer a version with writing-only access. Installation reporting is automatic, and removing this package can preserve the shared connection; revoke it in Beatra Console when you want access ended.

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 (34)

Description-Behavior Mismatch

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The reported wallet spending, media generation, voice modification, and task cancellation permissions substantially exceed a text-only copywriter's needs. If granted through a shared credential, those permissions could enable unauthorized charges or changes to unrelated resources following credential compromise or unintended tool invocation; the claim that this package is non-billable makes the mismatch especially significant.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High

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

Finding

As reported by the static analysis, generic remote-tool invocation and unrestricted-purpose local uploads expose more capability than conversation-only copywriting requires. User-selected uploads and disclosed installation reporting are not inherently exfiltration, but an insufficiently constrained upload path could transmit sensitive files to an unintended destination; the underlying code is not provided to verify consent and destination controls.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High

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

Finding

The supplied chunk contains no copywriting behavior. Its primary purpose is installation lifecycle and shared authorization management, including credential access, network revocation, and filesystem deletion that are not disclosed in the description. Although uninstall utilities can support a package, these shared-resource operations are materially beyond ordinary implementation details of generating copy. The script includes conservative inventory checks and a dry-run mode; those safeguards do not eliminate the description–behavior mismatch.

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 62)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/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 · 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/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 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.

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.

The copywriting skill requests unrelated financial and multimedia authorization privileges.

High

• Category: Excessive Agency
• Confidence: 99% confidence

Finding

The copywriting skill requests wallet spending, voice modification, video and music generation, and task cancellation privileges that are not justified by its stated text-copywriting purpose. Both credential loading and saving require the entire scope set, preventing use of a reduced-privilege credential and increasing the potential financial and account impact of token theft or unauthorized tool use; this file does not itself demonstrate misuse.

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.

The skill directs use of an external service and installation registration despite being a conversation-only copywriter.

Medium

• Category: Excessive Agency
• Confidence: 93% confidence

Finding

The manifest describes producing copy from a supplied brief, and the execution section explicitly says the entire deliverable is written in the current conversation without a generation task. Nevertheless, it directs use of a bundled client to contact Beatra and automatically register the installation, an external-service capability with no demonstrated role in drafting the requested text.

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).

The authorization workflow grants access to media and task capabilities beyond the copywriting skill's stated purpose.

Medium

• Category: Excessive Agency
• Confidence: 90% confidence

Finding

The documented approval grants access to image, video, music, speech, upload, model, and task tools, exceeding the copywriting skill's stated needs. This violates least privilege and increases the consequences of token theft or agent misuse, although this file does not establish the exact server-enforced permissions or demonstrate exploitation.

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 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 specifies recurring installation telemetry unrelated to its advertised copywriting purpose.

Medium

• Category: Excessive Agency
• Confidence: 96% confidence

Finding

The document specifies automatic, recurring transmission of a stable installation reference, installation provenance, network-route information, and runtime metadata without describing an explicit opt-in or a way to disable reporting. These fields can support persistent installation tracking and environment fingerprinting unrelated to generating copywriting content. The disclosed analytics purpose and stated exclusion of prompts, credentials, and file paths limit the apparent severity and do not establish malicious intent, but they do not eliminate the privacy concern; implementation behavior is not verified by this document alone.

Content

No source excerpt is available for this finding.

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

Medium

• Category: MCP Rug Pull
• Confidence: 85% confidence

Finding

The documented update command invokes an unpinned npm package through npx, which can download and execute a release that has not been reviewed. Although this is an optional, manually invoked CLI command rather than an MCP server configuration, a compromised package release could execute with the caller's permissions; the supplied file does not show automatic execution.

Content

No source excerpt is available for this finding.

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

Medium

• Category: MCP Rug Pull
• Confidence: 85% confidence

Finding

This is another occurrence of the same unpinned npx skills dependency in the update instructions, not a separate MCP server exposure. Following the command can execute an unreviewed npm release, but exploitation requires someone to invoke the documented command and encounter a malicious release.

Content

No source excerpt is available for this finding.