Back to skill
v1.0.1

Real mousic

ReviewClawScan verdict for this skill. Analyzed May 1, 2026, 8:39 AM.

Analysis

The skill matches its music-search purpose, but it can attach to an existing Chrome debugging session and kill processes on its chosen port, so it should be reviewed before installation.

GuidanceInstall only if you are comfortable with the skill launching and controlling Chrome through a debugging port. Before use, make sure port 9222 is not being used by another important Chrome session or local service, and prefer a version that verifies its own isolated browser profile before connecting or killing processes.

Findings (4)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Tool Misuse and Exploitation
SeverityMediumConfidenceHighStatusConcern
src/real_mousic/chrome_launcher.py
if is_port_open(port):
        pids = _find_pids_by_port(port)
        if pids:
            for pid in pids:
                _kill_pid(pid)

The cleanup logic finds and kills processes by port, without evidence that it verifies the process was launched by this skill or is actually Chrome.

User impactA user could lose work or disrupt another local tool if something else is using the selected port, especially the default Chrome debugging port 9222.
RecommendationOnly terminate the Chrome process that this skill started, verify the executable/profile before killing, and ask the user before closing an existing process.
Unexpected Code Execution
SeverityLowConfidenceHighStatusNote
src/real_mousic/xhs/stealth.py
Object.defineProperty(navigator, 'webdriver', { get: () => undefined }); ... STEALTH_ARGS = ["--disable-blink-features=AutomationControlled", ...]

The browser automation includes stealth JavaScript and Chrome flags intended to hide automation signals.

User impactThis is related to the scraping-style purpose, but it may violate website expectations or policies and is more invasive than ordinary browsing.
RecommendationClearly disclose the anti-detection behavior and provide a mode that uses normal browser automation without stealth features.
Agentic Supply Chain Vulnerabilities
SeverityLowConfidenceHighStatusNote
pyproject.toml
dependencies = [
    "requests>=2.28.0",
    "websockets>=12.0",
]

Dependency versions are open ranges, so installations may resolve to different package versions over time.

User impactThe install can change as upstream packages change, which affects reproducibility and supply-chain review.
RecommendationUse a checked-in lockfile or pinned dependency versions for reproducible installs.
Permission boundary

Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.

Identity and Privilege Abuse
SeverityMediumConfidenceHighStatusConcern
src/real_mousic/chrome_launcher.py
def ensure_chrome(...):
    if is_port_open(port):
        return True

The skill treats any already-open debugging port as usable instead of always launching or verifying its isolated profile.

User impactIf the configured port belongs to a user’s existing Chrome debugging session, the skill can control that browser context rather than a clean isolated one.
RecommendationRefuse to attach to unknown existing CDP endpoints, or verify they use the skill’s dedicated profile before connecting.