Back to skill

Security audit

audio-prompting

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent audio-prompting guide with expected references to audio/video tools, API credentials, uploads, and local ffmpeg workflows.

Install from a trusted source and consider pinning or pre-approving the `npx skills` installer before copying the install commands. Treat generated audio uploads and API keys as sensitive: only use the linked Pruna/Replicate workflows when intended, and avoid uploading private audio without consent.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (19)

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The skill instructs users to install and invoke npx skills without pinning an exact package version or immutable artifact. npx resolves packages dynamically, so a future compromised or maliciously replaced package version could be fetched and executed, creating a supply-chain execution risk on the user's machine.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

This line references npx skills in an installation command without an explicitly pinned tool version. Because npx may download and execute the latest matching package at runtime, an attacker controlling the package distribution path or a compromised upstream release could achieve arbitrary code execution.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The install command at this location uses npx skills without pinning the executable's version, exposing consumers to supply-chain drift. If the package or its dependencies are tampered with, following the documented command can execute attacker-controlled code.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

This unpinned npx skills command allows execution of whatever package version is resolved at invocation time. That increases exposure to malicious upstream updates, typosquatting, or dependency compromise leading to arbitrary command execution.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The skill's documentation includes another npx skills installation example that is not version-pinned. In practical terms, users copying this command may execute a newer or compromised tool release than the author intended, enabling supply-chain compromise.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

An unpinned npx skills invocation is present here, which creates a trust-on-first-use dependency on the current state of the package registry. If the registry artifact changes maliciously, the command can run arbitrary code on the host.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The documented npx skills command is unpinned and therefore susceptible to package substitution or compromised release delivery. Because npx executes the retrieved package, the consequence is code execution rather than merely incorrect output.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

This line repeats the same unsafe pattern: runtime execution of npx skills without a pinned version. In a skill-distribution context, repeated copy-pasteable commands widen the chance that users execute a compromised upstream package.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The related-skill installation command uses unpinned npx skills, which means execution depends on mutable external package state. A malicious or hijacked package release could result in arbitrary code execution when a user follows the documentation.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

This command again relies on unpinned npx skills, introducing a supply-chain attack surface in documentation that users are expected to copy verbatim. The danger is amplified because the command executes code immediately after fetching it.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The skill recommends another unversioned npx skills invocation, which is a true supply-chain risk rather than a harmless documentation style issue. Anyone following it may fetch and run an unintended or compromised package version.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

This model-specific install snippet still uses unpinned npx skills, so it inherits the same registry and dependency-chain compromise risk. Since npx executes the package on retrieval, exploitation can directly impact the local environment.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The documentation includes an unpinned executable package fetch via npx skills. That makes the command non-reproducible and vulnerable to malicious package updates or dependency hijacking that could execute arbitrary code.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

This installation example also executes npx skills without constraining the resolved version. In a public package ecosystem, that is a genuine supply-chain weakness because package contents can change independently of the skill documentation.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

An attacker who compromises the package or dependency tree resolved by this unpinned npx skills command could gain code execution on systems following the skill instructions. The issue is documentation-driven but still security-relevant because it prescribes executable behavior.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

This line repeats the same pattern of unpinned remote code execution through npx skills. The audio-prompting context does not reduce the danger because the risk stems from package installation mechanics, not domain content.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The install command uses npx skills without a fixed version, which is vulnerable to unexpected or malicious package changes in the registry. Because the command is intended for user execution, this is a practical supply-chain attack vector.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

This unpinned npx skills example exposes users to arbitrary code execution if the resolved package or one of its dependencies becomes compromised. The risk is moderate because exploitation depends on an upstream compromise, but the resulting impact on the local machine can be severe.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The 'full suite' command uses npx skills without pinning, making it the broadest instance of the same supply-chain issue because it encourages installation of a larger package set through a mutable executable path. If abused, it could compromise systems that trust the documentation and run the command as-is.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.