Security audit

Spotify控制

Security checks for vulnerabilities and agentic risk

Overview

This Spotify control skill is mostly purpose-aligned, but its dependency mismatch and broad state-changing controls need human review before installation.

Review the dependency before installing: confirm which Spotify CLI is intended, install it from a trusted source, and avoid letting broad trigger phrases run playlist or volume changes without explicit confirmation.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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 (1)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:4
Finding: Unpinned and Inconsistent Third-Party CLI Dependency
Content: View full analysis
list: result = subprocess.run( [self.cmd_prefix, "search", query, "--json"], capture_output=True, text=True ) if result.stdout: return json.loads(result.stdout) return [] def now_playing(self) -> dict: result = subprocess.run( [self.cmd_prefix, "status", "--format", "json"], capture_output=True, text=True ) if result.stdout: return json.loads(result.stdout) return {} def set_volume(self, level: int): subprocess.run([self.cmd_prefix, "volume", str(level)], capture_output=True) ``` ### Technical Analysis The skill defines three inconsistent dependency identities: `spotifyd`, `spotify-cli`, and `spicetify-cli`/`spicetify`. It neither pins an audited version nor identifies a verified package source or publishe ...[truncated 1621 chars]
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill metadata declares required binaries as spotifyd and spotify-cli, while the implementation and examples actually invoke spicetify. This mismatch can cause users or automation to install/approve one toolset while the skill executes another, undermining trust, dependency review, and least-privilege expectations.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The activation phrases include very broad triggers such as Spotify, 播放音乐, and 控制音乐, which can match ordinary conversation or unrelated music requests. In an agent setting, that raises the chance of unintended invocation and unauthorized playback or account-modifying actions without clear user intent.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill advertises playlist management but does not warn that these operations can create or alter user playlists tied to their Spotify account. In context, this makes accidental or socially engineered data modification more likely because users may not realize the skill performs persistent account changes rather than read-only playback control.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.