Back to skill

Security audit

KYC Guide Set

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly transparent about generating KYC guide images, but it also grants broad Beatra account access, can spend credits, and silently self-updates installed code.

Review before installing. Only use this skill if you are comfortable giving Beatra a persistent shared device token that can spend credits and access more media capabilities than KYC image generation requires. Consider disabling automatic updates with the provided update control, revoke access from the Beatra Console when done, and avoid uploading sensitive local files unless they are truly needed as references.

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
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (3)

T05 · Unauthorized Access and Privilege Escalation

Error
Location
scripts/authorize.py:32
Finding

Overprivileged Shared Device Token and Unrestricted Tool Dispatch

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's declared function is to generate KYC guide images from user-supplied checklist text. This requires image generation, optional artifact upload, model discovery, task status access, and limited wallet information. However, the requested Device Token additionally authorizes video generation, music generation, speech generation, voice-resource writes, wallet spending, artifact reads, and task cancellation. The credential is also documented as shared by all installed Beatra Skills. The lo ...[truncated 1622 chars]
Remediation
View remediation

T03 · Remote Payload Retrieval and Execution

Error
Location
scripts/mcp_client.py:515
Finding

Silent Automatic Retrieval and Replacement of Executable Package Code

Content
View full analysis
dict[str, Any]: path = update_home / "state.json" try: value = json.loads(path.read_text(encoding="utf-8")) except (OSError, json.JSONDecodeError): return {"schema_version": 1, "auto_update": True} if not isinstance(value, dict) or value.get("schema_version") != 1: return {"schema_version": 1, "auto_update": True} return value ``` Ordinary commands silently retrieve and apply updates: ```python def maybe_auto_update( *, state_dir: Path | None = None, install_root: Path | None = None, get_bytes: GetBytes = _default_get_bytes, now: float | None = None, ) -> 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("aut ...[truncated 3500 chars]
Remediation
View remediation

other

Note
Location
scripts/authorize.py:340
Finding

Collection and Transmission of Hostname and Stable Environment Metadata

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" ``` It also collects the local hostname: ```python 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] ``` The collected hostname is transmitted during Device Authorization: ```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": ...[truncated 2390 chars]
Remediation
View remediation
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (44)

Context-Inappropriate Capability

Critical
Category
Not specified by scanner
Confidence
100% confidence
Finding

Requesting wallet:spend plus unrelated generation scopes for a checklist-to-guide KYC graphics skill creates an unnecessarily dangerous authorization grant. If the credential is abused, an attacker or buggy skill could incur charges, generate unrelated content, or operate against the user's account in ways the user would not expect from this package.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill includes uninstall and package-removal behavior unrelated to generating KYC guide content, along with local state inspection and token revocation. Such hidden lifecycle-management capabilities can be abused to alter the local environment, remove files, or manipulate authorization state under the guise of a content-generation skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill includes uninstall and package-removal behavior unrelated to generating KYC guide content, along with local state inspection and token revocation. Such hidden lifecycle-management capabilities can be abused to alter the local environment, remove files, or manipulate authorization state under the guise of a content-generation skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill includes uninstall and package-removal behavior unrelated to generating KYC guide content, along with local state inspection and token revocation. Such hidden lifecycle-management capabilities can be abused to alter the local environment, remove files, or manipulate authorization state under the guise of a content-generation skill.

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 89)May include surrounding context.

md
Submit once through bundled `scripts/mcp_client.py`. Poll

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 117)May include surrounding context.

md
Submit once through bundled `scripts/mcp_client.py`. Poll

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 121)May include surrounding context.

md
Submit once through bundled `scripts/mcp_client.py`. Poll

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 129)May include surrounding context.

md
Submit once through bundled `scripts/mcp_client.py`. Poll

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 180)May include surrounding context.

md
Submit once through bundled `scripts/mcp_client.py`. Poll

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 181)May include surrounding context.

md
Submit once through bundled `scripts/mcp_client.py`. Poll

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 182)May include surrounding context.

md
Submit once through bundled `scripts/mcp_client.py`. Poll

Credential Access

High
Category
Privilege Escalation
Confidence
97% confidence
Finding

Referencing a local credential file means the skill is configured to use bearer credentials from the user environment, which is sensitive material. In the context of a KYC guide generator, that access is especially dangerous because it is unrelated to the stated functionality and could allow unauthorized use of the user’s Beatra account or access to protected remote resources.

Content

Scanner excerpt · manifest.json (reported line 53)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.

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

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The OAuth scope string grants many capabilities unrelated to a KYC guide still generator, including artifacts, speech, music, video, task control, and wallet spending. This violates least privilege and means that if the token is issued, compromise or misuse of the skill could access or spend from the user's account well beyond the stated purpose.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The client implements a full self-update mechanism that downloads manifests and archives from remote infrastructure, validates them, and then overwrites files in the local installation. Even with checksum and path checks, this gives the remote service ongoing code-execution influence over the installed skill, which is far broader than a KYC-guide generation skill needs and materially increases supply-chain risk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The upload() path reads any local regular file supplied by path and sends its bytes to a remote service after obtaining an upload grant. For a skill advertised as converting checklist lines into KYC guide stills, arbitrary local file exfiltration is overbroad capability and dangerous if exposed through an agent workflow or prompt-mediated tool use.

Content

No source excerpt is available for this finding.

Self-Modification

High
Category
Rogue Agent
Confidence
98% confidence
Finding

The skill exposes self-update functionality that can replace its own installed files, amounting to self-modification. In a skill whose declared purpose is static KYC guide generation, self-modifying behavior is unjustified and significantly raises supply-chain and persistence concerns because future code can change independently of the original reviewed package.

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",

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The uninstall script handles shared device credentials and revokes them against a remote service, which is unrelated to the advertised KYC guide-generation purpose of the skill. This creates hidden authority over a broader Beatra account context and expands the blast radius beyond this package, especially because it operates on shared state under ~/.beatra rather than package-local data.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
92% confidence
Finding

Referencing credentials.json as part of the state owned and deleted by the uninstall flow confirms the skill is designed to interact with shared credential storage. Even if the file is only removed during uninstall, coupling a content-generation skill to credential-bearing state is an unnecessary privilege that increases risk if the script is modified, misused, or triggered unexpectedly.

Content

Scanner excerpt · scripts/uninstall.py (reported line 40)May include surrounding context.

python
#: these and then removes the directory only if it is empty — the script
#: never recursively deletes a directory it does not fully understand.
_STATE_FILES = (
    "credentials.json",
    "installation.json",
    "host.json",
    "skills.json",