Security audit

Ai Media Cli

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward guide for installing and using an AI media CLI, but users should handle API keys carefully and understand that prompts and media go to ricebowl.ai.

Before installing, verify that ai-media-generator is the intended package from the expected publisher, prefer an isolated non-admin install, use a dedicated limited API key, avoid pasting real keys into chat or logs, and do not submit confidential prompts, images, URLs, or metadata unless ricebowl.ai is approved for that data.

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: references/cli-commands.md:5
Finding: Unpinned Third-Party CLI Packages Installed from Multiple Registries
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (9)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The description says to use this skill when someone wants to 'install, configure, onboard, script, or troubleshoot' the ai-media CLI, which is a wide set of intents without explicit exclusion boundaries. Although the product name narrows it somewhat, the trigger guidance does not specify when to prefer this skill versus adjacent skills except for one limited case later in the file.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The operational instructions are written in Chinese, and the document does not indicate that the skill is intended only for Chinese-speaking users or that language should follow user preference. This can violate language/locale policy because it imposes a specific language without opt-in.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill instructs users to set and then display configuration around an API key, but gives no warning not to paste secrets into chat, logs, screenshots, or shared terminals. In a credential-handling onboarding flow, that omission increases the chance of accidental secret exposure, especially because config show may reveal whether a key is present or expose sensitive values depending on CLI behavior.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The documentation explicitly encourages storing an API key locally and printing the current configuration, but it does not warn that config show may expose secrets in terminal history, logs, screenshots, or CI output. In an agent/automation context, this increases the chance that credentials are unintentionally disclosed and reused by others.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: These commands submit prompts, image URLs, and metadata to a remote service, but the documentation does not clearly disclose that user-supplied content leaves the local machine and is processed by ricebowl.ai. Users may unknowingly send proprietary, personal, or regulated content to an external platform, especially when following automation-oriented examples.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The video generation section similarly instructs users to send prompts and reference images to a network-backed service without an explicit warning about remote transmission. Because video workflows often involve richer media and automation, the omission raises the risk of accidental disclosure of confidential visual material or embedded metadata.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The onboarding doc instructs users to pass a plaintext API key directly on the command line and optionally export it in the shell, but it does not warn that command-line arguments can be stored in shell history and visible to other local users via process inspection. In a CLI onboarding context, this is more dangerous because new users are likely to copy-paste the examples verbatim, increasing the chance of credential exposure and subsequent unauthorized API usage.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 96% confidence
Finding: Most of the instructional content in this file is presented in Chinese, while there is no indication that the user can choose another language or that the document is intentionally region-specific. The policy requires flagging natural-language locale constraints when a specific language is effectively forced without opt-in or justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The onboarding content presents substantial user-facing guidance in Chinese while other parts of the document are in English, with no indication that the language choice is optional or region-specific. This can amount to a language/locale policy concern because the document implicitly fixes part of the user experience to a specific language without opt-in.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.