Back to skill

Security audit

Viral Titles and Topics

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because scanners report broad account permissions, media-generation and file-upload capabilities, telemetry, and shared connection management beyond its stated title-and-topic purpose.

The verdict is suspicious, not malicious. Consider whether you need this skill’s extra media, upload, telemetry, and account-management features, and whether you are comfortable granting a shared token with spending and other broad permissions. Skillspector reports partial analysis: all listed components were scanned, but several referenced items 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (38)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

Paid image, speech, video, and cancellation capabilities are explicitly described, so those portions are not unexplained behavior. However, the reported music-generation and voice-write permissions exceed this workflow's needs; granting them unnecessarily increases the consequences of credential compromise or agent misuse.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

Uploading a user-supplied photo is documented and is not inherently exfiltration. The reported automatic transmission of a persistent installation identifier and environment metadata creates a separate privacy concern not necessary for title generation, while unrestricted tool dispatch can amplify excessive authorization if no enforcement exists outside the client.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied chunk implements connection teardown and local-state cleanup, not public-post research or title/topic generation. Although uninstalling is a legitimate package-maintenance operation, these shared-credential and authorization-management capabilities are materially outside the declared content workflow. The script includes safeguards to retain the connection when other installations may need it, but those safeguards do not make its behavior represented by the description.

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 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 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 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
92% confidence
Finding

The concern is not the credential filename but the explicit sharing of one full-scope bearer token across all packages without fresh authorization. A compromised package able to read that token can inherit unrelated account capabilities, increasing the potential for unauthorized spending and cross-package actions.

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.

Authorization requests media-generation, voice-management, and spending capabilities unrelated to title and topic research.

High
Category
Excessive Agency
Confidence
99% confidence
Finding

Authorization unconditionally requests spending, media-generation, and voice-write permissions beyond what title and topic research requires. The script also requires an exact match to this broad scope set, preventing use of a reduced-scope credential; misuse of the resulting bearer token could therefore spend credits or perform unrelated account operations.

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/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):

Malformed inventory entries are silently discarded, contradicting the documented rule that uncertainty must preserve the shared connection.

High
Category
Excessive Agency
Confidence
98% confidence
Finding

The inventory loader silently drops non-dictionary entries rather than treating the inventory as untrustworthy. If those entries represent other installed skills, the uninstall logic can incorrectly conclude that no survivors remain, revoke the shared device credential, and delete shared state. This affects every skill using the connection, making it more consequential than cleanup confined to this title-generation package.

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 title-and-topic workflow also directs paid image, speech, and video production, which the manifest does not disclose.

Medium
Category
Excessive Agency
Confidence
94% confidence
Finding

The manifest at L03 describes reading public posts and writing topics, hooks, and titles. L36–L38 additionally direct photo uploads, image generation and editing, speech synthesis, and video animation and composition; these produce multimedia assets rather than merely implementing the stated writing workflow. Although the workflow requires confirmation before paid calls, these additional capabilities remain absent from the manifest description.

Content

No source excerpt is available for this finding.

The FAQ directs image modification beyond the declared title-and-topic workflow.

Medium
Category
Excessive Agency
Confidence
90% confidence
Finding

L17 instructs the agent to call beatra.images.edit to change a cover image and then deliver that cover. The manifest describes reading public posts and producing textual titles and topic lists; modifying visual assets is an additional operation, not a necessary implementation detail of that workflow.

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).

The authorization flow grants capabilities unrelated to public-post research and title generation.

Medium
Category
Excessive Agency
Confidence
91% confidence
Finding

One authorization covers multiple media capabilities, including music, rather than limiting access to the package's required operations. Reusing the same credential across packages without narrower authorization increases the blast radius of a compromised package or misdirected agent.

Content

No source excerpt is available for this finding.

The workflow records installation-source metadata inferred from the conversation without disclosing this collection to the user.

Medium
Category
Output Handling
Confidence
86% confidence
Finding

The workflow silently derives installation-source attribution from conversation context and records it despite this being unnecessary for the user's creative task. The fixed category list limits sensitivity, but this remains secondary use of conversational information without a user-facing choice.

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 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