Back to skill

Security audit

AI批量短视频生产工作流|AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches an AI-HIVE video-generation workflow, but it can persist an API key and send it to a configurable API host without validation, which creates a real credential-disclosure risk.

Install only if you are comfortable with a paid AI-HIVE workflow that stores an API key locally and uploads selected media. Do not use custom --base-url or AI_HIVE_BASE_URL values unless you fully trust the endpoint; prefer the default AI-HIVE host, review ~/.ai-hive/config.json for unexpected base_url changes, and use a limited/revocable API key where possible.

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 (1)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/videogen.py:91
Finding

Unrestricted API Endpoint Allows Bearer Credential Disclosure

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (12)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

This finding indicates undeclared generic text chat, image generation, wallet/user-info queries, and model-listing capabilities beyond the stated purpose. Undeclared capabilities are especially risky in a skill that may touch paid APIs and user assets, because they can expand the attack surface, expose account metadata, and enable actions outside the user's informed consent.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

This finding indicates undeclared generic text chat, image generation, wallet/user-info queries, and model-listing capabilities beyond the stated purpose. Undeclared capabilities are especially risky in a skill that may touch paid APIs and user assets, because they can expand the attack surface, expose account metadata, and enable actions outside the user's informed consent.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill advertises executable commands and API-driven workflows but does not declare any explicit tool scope or allowed-tools boundary. In an agent environment, this can lead to over-broad access to environment variables, filesystem, shell, and network capabilities, increasing the chance of unintended secret exposure, arbitrary command execution, or unsanctioned outbound requests.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description and invocation section define the skill entirely through Chinese trigger phrases and Chinese-language usage framing, with no indication that users may interact in other languages or choose their preferred locale. This is a natural-language locale policy concern because the skill appears to require a specific language context rather than explicitly offering a choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The phrase production-ready Chinese workflow imposes a specific language/locale behavior in the skill's natural-language instructions. The file does not offer the user a language choice or explain why Chinese is required, which conflicts with the policy against forcing a locale without opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill enables implicit invocation without narrowing when it may trigger, which can cause the agent to activate this capability in broader contexts than intended. Because this skill can generate production-ready workflows and runnable AI-HIVE commands for batch video generation, overbroad auto-invocation increases the risk of unintended use in sensitive, non-consensual, or policy-violating content pipelines.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file advertises and implements a broad generic AI API wrapper (text chat, image generation, video generation, model listing, media upload, task polling) rather than a narrowly scoped batch short-video production skill. Over-broad capability increases attack surface and enables unintended use cases outside the declared manifest scope, weakening least-privilege and making policy bypass or misuse easier.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The module docstring and all user-facing CLI guidance are written only in Chinese, and the skill metadata/example at the end also frames usage exclusively in Chinese. This creates a natural-language locale constraint without any explicit opt-in or documented justification, which matches the policy-violation category for forced language/locale behavior.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The generic text chat endpoint is unrelated to the stated batch short-video production purpose and can be used as an unrestricted auxiliary LLM capability. That scope expansion can enable prompt injection pivoting, off-policy content generation, or repurposing the skill for unintended tasks beyond its declared function.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Standalone image generation exceeds the declared video-batch-production scope and creates an additional content-generation surface not required by the manifest. Extra modality support increases misuse potential and complicates review, logging, and policy enforcement, especially in an automation-oriented skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The file’s docstring, argparse description, and emitted skill name are all hard-coded in Chinese, with no indication that users can select another language or locale. Under the policy rule for natural-language constraints, this is a locale/language preference embedded in the skill without explicit opt-in or documented justification.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill can query user account information and wallet balance even though that is not necessary for batch video production. Unnecessary account-access features expand the available data surface and may reveal sensitive billing or identity details if invoked by an untrusted workflow or prompt chain.

Content

No source excerpt is available for this finding.