Security audit

Audio Broadcast

Security checks for vulnerabilities and agentic risk

Overview

This broadcast-control skill is mostly coherent, but it ships a concrete admin token and handles credentials over cleartext HTTP and plaintext files.

Review this skill before installing. Do not use the bundled token; revoke or replace it, delete config.json, and log in only against a trusted server. Avoid remote use unless the service is protected by HTTPS or a secure tunnel. Treat TTS text as potentially sent to an external provider, and only enable scheduled cleanup if you are comfortable with automatic deletion of server-side TTS files.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (5)

T09 · Insecure Skill Coding Practices

Error

Location: config.json:1
Finding: Active Authentication Token Distributed in Project Configuration
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Error

Location: scripts/xiaoboshu.py:100
Finding: Passwords, Tokens, Management Requests, and Audio Uploads Sent over Cleartext HTTP
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/xiaoboshu.py:93
Finding: Authentication Token Persisted in a Predictable Plaintext File without Permission Hardening
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/xiaoboshu.py:614
Finding: Login Password Exposed through Command-Line Arguments
Content: View full analysis
") sys.exit(1) login(sys.argv[2], sys.argv[3], sys.argv[4]) ``` The documented invocation requires the same pattern: ```bash python scripts/xiaoboshu.py login ``` ### Technical Analysis The password is required as a positional command-line argument. Depending on the operating system and execution environment, command arguments may be visible in process listings, process-monitoring tools, shell history, terminal transcripts, automation logs, Agent tool-call records, or audit telemetry. Authentication is necessary for the declared functionality, but putting the password in `argv` is not necessary. Interactive secret input or a protected secret provider would avoid most of this exposure. ### Attack Path 1. A user follows the documented login syntax and includes the password directly in the command. 2. The shell records the command in history, or the operating system exposes the active process arguments. 3. A local user, monitoring agent, log collector, or person with access to execution records reads the command. 4. The attacker extracts the username and password. 5. The attacker authenticates to the Xiaoboshu service and receives a valid token. ### Impact Assessment The exposed value is the reusable account password rather than only a single request parameter. If the password remains valid, an attacker can authenticate repeatedly and may obtain fresh tokens. The resulting scope is determined by the affected account and may include control of broadcast devices, files, playback, volume, and scheduled tasks. ]]>
Remediation: View remediation

other

Warning

Location: scripts/xiaoboshu.py:487
Finding: User-Provided TTS Text Sent to an External Service without Clear Privacy Disclosure
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (76)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 95% confidence
Finding: The manifest presents the skill as a broadcast-control interface, but the documentation also describes housekeeping behavior that deletes server-side TTS files and performs cleanup based on task references. That mismatch is security-relevant because users and orchestrators may grant trust for playback operations while the skill also performs destructive maintenance actions that can remove data or disrupt scheduled content if used incorrectly.
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 32)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 51)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 64)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 70)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 80)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 86)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 92)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 124)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 146)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 153)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 156)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 159)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 162)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 165)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 168)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 171)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 174)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 177)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 186)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 189)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 198)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 201)May include surrounding context.
md
python scripts/xiaoboshu.py login <host> <username> <password>

Static analysis

No suspicious patterns detected.