Back to skill

Security audit

AI Character Design Sheet & Consistency Studio

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent Beatra image-generation purpose, but it asks for broad account-level media and spending authority and can silently update its own code.

Install only if you trust Beatra with a reusable broad device token that can spend credits and access multiple media/tool categories, not just character images. Consider disabling silent updates with the documented update command and revoke the Beatra device authorization from the console when you no longer need the skill.

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 (2)

T05 · Unauthorized Access and Privilege Escalation

Error
Location
scripts/authorize.py:31
Finding

Over-Privileged Device Authorization and Unrestricted MCP 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 is declared as a character-image generation utility. Its legitimate requirements include image generation and transformation, reference-image upload, model discovery, and task management. The authorization request nevertheless obtains permissions for unrelated capabilities, including: - Video generation - Music generation - Speech generation - Voice creation and modification - General wallet spending - Broad artifact access - Task cancellation across the shared authorization context The local MCP client compounds this excessive scope by accepting an arbitrary `tool_name` from the command line and forwarding it through `tools/call`. It does not enforce a package-specific allowlist before attaching the full-scope bearer token. The bearer token is ...[truncated 1641 chars]
Remediation
View remediation

T03 · Remote Payload Retrieval and Execution

Error
Location
scripts/mcp_client.py:969
Finding

Default Silent Remote Code Update Without an Independent Authenticity Trust Anchor

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( install_root=resolved_root, update_home=update_home, get_bytes=get_bytes, ) discovery = checked["discovery"] manifest, new_files = download_update(discovery, get_bytes=get_bytes) _apply_updat ...[truncated 3700 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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (44)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill's described function does not suggest it can inspect installation inventory, delete local credential/state files, revoke OAuth/device authorization, or manage shared authorization across skills. Those lifecycle and account-management actions are security-sensitive; if bundled into a creative skill without prominent disclosure, they can surprise users and create opportunities for misuse or destructive actions.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill's described function does not suggest it can inspect installation inventory, delete local credential/state files, revoke OAuth/device authorization, or manage shared authorization across skills. Those lifecycle and account-management actions are security-sensitive; if bundled into a creative skill without prominent disclosure, they can surprise users and create opportunities for misuse or destructive actions.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill's described function does not suggest it can inspect installation inventory, delete local credential/state files, revoke OAuth/device authorization, or manage shared authorization across skills. Those lifecycle and account-management actions are security-sensitive; if bundled into a creative skill without prominent disclosure, they can surprise users and create opportunities for misuse or destructive actions.

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 58)May include surrounding context.

md
Submit it once with the package's bundled `scripts/mcp_client.py`, retain

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 97)May include surrounding context.

md
Submit it once with the package's bundled `scripts/mcp_client.py`, retain

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 101)May include surrounding context.

md
Submit it once with the package's bundled `scripts/mcp_client.py`, retain

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 102)May include surrounding context.

md
Submit it once with the package's bundled `scripts/mcp_client.py`, retain

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 135)May include surrounding context.

md
Submit it once with the package's bundled `scripts/mcp_client.py`, retain

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 136)May include surrounding context.

md
Submit it once with the package's bundled `scripts/mcp_client.py`, retain

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 137)May include surrounding context.

md
Submit it once with the package's bundled `scripts/mcp_client.py`, retain

Credential Access

High
Category
Privilege Escalation
Confidence
89% confidence
Finding

The manifest declares a local credential file path for bearer authentication, which means the skill depends on reusable local secrets being available to access a remote MCP endpoint. While not automatically exploitable from this file alone, referencing a persistent credential store increases the blast radius if the skill runtime, logs, or surrounding tooling expose file paths or tokens, and it can normalize unnecessary secret access for a content-generation skill.

Content

Scanner excerpt · manifest.json (reported line 65)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
98% confidence
Finding

The OAuth scope string requests a very broad set of capabilities, including artifacts, images, videos, music, speech, voices, tasks, and wallet spending, which exceeds the stated purpose of a character visual-pack skill. Over-scoped tokens violate least privilege and materially increase blast radius if the token is misused, leaked, or the skill is repurposed.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The scope includes videos:generate even though the skill description centers on reusable character sheets, portraits, poses, expressions, scenes, and mascots. Even if short videos are mentioned in the description, bundling video generation into the same broad default token still expands privilege and risk beyond the core image-focused workflow.

Content

No source excerpt is available for this finding.

Self-Modification

High
Category
Rogue Agent
Confidence
96% confidence
Finding

The skill exposes self-modification behavior via its update command and broader self-update framework, allowing code in the installed package to be replaced. In the context of an agent skill whose stated purpose is character consistency generation, self-modification is unnecessary and dangerous because it expands the attack surface from using the skill to changing the skill's future behavior.

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",

Credential Access

High
Category
Privilege Escalation
Confidence
90% confidence
Finding

The script declares credentials.json as part of the removable shared state, indicating the package is aware of and authorized to act on stored authentication material. In the context of an ordinary content-generation skill, direct handling of credential files is overprivileged and increases the risk of credential misuse, unintended logout of other skills, or future code changes turning this access into token exfiltration.

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",

Credential Access

High
Category
Privilege Escalation
Confidence
96% confidence
Finding

The _device_token function reads an access token directly from ~/.beatra/credentials.json and passes it to the revocation flow. Direct token access by a non-auth skill is sensitive because it grants the package visibility into bearer credentials that could be repurposed for unauthorized API calls or account/device disruption if the code were modified or compromised.

Content

Scanner excerpt · scripts/uninstall.py (reported line 109)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):

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill invokes a bundled Python client, performs network calls, reads and writes local state, and supports updates, but the manifest declares no explicit tool scope or permission boundaries. That omission weakens least-privilege controls and makes it harder for users or the host to understand and constrain what the skill can do.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill includes a self-updating mechanism that downloads and installs new package versions, which is unrelated to the core character-image workflow and materially expands the trust boundary. Any auto-update path is a code-execution and supply-chain risk: compromise of the update channel, signing/verification process, or package publisher could lead to silent installation of malicious code.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.