Security audit

Seedance 2.5 电商视频

Security checks for vulnerabilities and agentic risk

Overview

The skill’s purpose is coherent, but its file-transfer script has a real transport-validation weakness that could expose user-selected product media or write oversized/untrusted downloads if the API or storage endpoint redirects unexpectedly.

Install only if you trust the AI Hive service and are comfortable uploading the selected product images/videos to it. Prefer `--preview` first, use `--no-download` when you only need the task ID, keep the API key scoped and protected, and consider pinning dependencies or isolating the script before processing sensitive product assets.

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 (2)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/listing_clips.py:213
Finding: HTTPS Enforcement Can Be Bypassed Through Redirects
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Note

Location: SKILL.md:168
Finding: Runtime Dependency Installation Is Not Version-Pinned
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 95% confidence
Finding: The skill invokes shell commands, reads local files, may write outputs, uses environment variables, and performs networked API calls, but it does not declare any explicit tool scope or permission boundaries. This creates a least-privilege failure: an agent or reviewer cannot tell from metadata what capabilities are expected, increasing the chance of overbroad execution, unsafe secret exposure, or unintended filesystem/network access.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The manifest description says to use the skill for a very broad set of phrases and domains, including generic terms like '电商视频', '商品主图视频', '详情页视频', 'Listing', and 'PDP'. Without clearer trigger constraints or negative examples, these common terms could cause unintended activation during ordinary ecommerce content discussions.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The file’s natural-language interface is entirely in Chinese, including the module docstring and user-facing error/help strings, with no indication that users may choose another language. This creates a language/locale policy concern because the skill appears to require a specific language without explicit opt-in or a documented region-specific justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: The primary skill description is written predominantly in Chinese and does not indicate that users may choose another language or that the skill is intentionally limited to a Chinese-speaking context. Per the policy, forcing a specific language without user opt-in can be a natural-language policy issue unless the locale restriction is explicit and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The example value includes Chinese-only instructional text ("请替换为你的APIKey"), which imposes a specific language in a user-facing configuration artifact. There is no indication that the skill is region-specific or that users may choose their preferred language, so this is a natural-language locale policy concern.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.