Security audit

Seedance 2.5 社交电商回复视频

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a legitimate AI Hive video-generation helper, but users should protect their API key and only upload media they are allowed to share.

Install in an isolated Python environment, avoid entering the API key directly in a shell command where it may be logged, prefer a protected environment variable or carefully managed config file, and upload only product images or videos that are approved to leave your machine for AI Hive processing.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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

Findings (3)

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:159
Finding: API Key Exposed Through Command-Line Arguments
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Note

Location: SKILL.md:158
Finding: Unpinned Third-Party Dependency Installation
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/comment_reply.py:216
Finding: Media Upload Destination and Method Are Controlled by the API Response Without Host Allowlisting
Content: View full analysis
Remediation: View remediation

SkillSpector

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
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (7)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 91% confidence
Finding: The skill invokes a Python script, performs package installation, and references API keys, task status checks, files, and networked model calls, yet it does not declare any explicit tool/permission boundaries. That mismatch increases the chance an agent grants broader shell, file, environment, and network access than intended, which can lead to unintended command execution, secret exposure, or filesystem/network abuse if the skill is triggered in a permissive runtime.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The description contains many broad trigger phrases spanning social commerce, video replies, product Q&A, livestream clips, comparisons, and multiple platforms/models, without strong activation conditions. In an agent ecosystem, this can cause over-broad auto-matching and accidental invocation on loosely related user requests, which is risky because the skill has operational capabilities and handles potentially sensitive customer-comment workflows.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The description is primarily written in Chinese and presents the skill as operating in that locale by default, while also covering global platforms such as Instagram and TikTok Shop. There is no explicit statement that users may choose output language or locale, nor a documented reason that the skill is intentionally limited to Chinese-language use.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: This Python skill presents its top-level description and user-facing error/help strings in Chinese only, starting with the module docstring and continuing through CLI-facing messages. For a general-purpose skill, forcing a single language without offering a user choice or documenting a justified locale restriction is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The manifest describes a skill for turning social-commerce questions into traceable Seedance 2.5 reply videos via AI Hive. The auth command goes beyond that content-generation purpose by persisting API credentials to ~/.ai-hive/config.json, which is an account/setup function rather than a direct requirement of creating reply videos.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The placeholder text 请替换为你的APIKey is presented only in Chinese, which imposes a specific language in user-facing natural language content. The file does not offer an alternative language or explain a region-specific reason for this constraint, so it may violate language/locale policy expectations.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Low

Category: Not specified by scanner
Confidence: 70% confidence
Finding: The manifest focuses on transforming comments/DMs/synthetic questions into traceable social-commerce reply shorts. The separate status command exposes a generic generation-task lookup capability by task ID, which is not clearly justified by the stated purpose of producing a reply clip from supplied commerce inputs.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.