Back to skill

Security audit

Etsy 电商视频生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches Etsy video creation, but it handles API keys and media uploads through a configurable API endpoint without enough safeguards.

Install only if you are comfortable giving this skill an AI Hive API key and uploading selected product media to AI Hive. Keep the base URL at the official HTTPS endpoint, protect ~/.ai-hive/config.json, avoid wrapper scripts or environment variables that set AI_HIVE_BASE_URL, and prefer installing dependencies in a controlled environment with pinned versions.

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)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:64
Finding

Unpinned Runtime Dependency Installation

Content
View full analysis
Remediation
View remediation
``` 2. Generate and verify cryptographic hashes for every direct and transitive dependency, then install with: ```bash python3 -m pip install --require-hashes -r requirements.txt ``` 3. Use a lock-file workflow that records the complete dependency graph. 4. Install dependencies inside a dedicated virtual environment rather than the system Python environment. 5. Use only a trusted package index and explicitly configure the index URL in controlled deployment environments. 6. Integrate dependency vulnerability and integrity scanning into release maintenance. ]]>

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/videogen.py:90
Finding

Bearer API Key Can Be Sent to an Arbitrary Configurable Endpoint

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 (10)

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The file implements a broad AI Hive client with capabilities far beyond the declared Etsy video-generation/editing purpose, including text chat, image generation, model enumeration, account lookup, and generic media upload. This violates least-privilege and creates a capability-expansion risk: any agent or user invoking this skill gains access to unrelated actions that could be abused for data access, policy bypass, or unintended billing/asset generation.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill invokes shell commands, installs packages, accesses files, and makes likely network-backed API calls via the Python script, but it declares no explicit tool or permission scope. That creates an over-privileged execution model where an agent may grant broader capabilities than necessary, increasing the blast radius if the script is modified, compromised, or misused.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file's manifest-style description says 'Use this skill for Etsy商品视频、手作过程、个性化定制...和Listing演示', which is a wide natural-language activation description rather than a specific, bounded trigger. It does not define exact trigger phrases, scope limits, or negative examples, so ordinary Etsy-related requests could match unintentionally.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The visible skill instructions and headings are written in Chinese, and the file does not state that users may choose another language or locale. This can violate language-choice policy when the skill appears to impose one language by default without opt-in.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The module describes itself as a general-purpose AI capability tool, which contradicts the manifest’s Etsy-specific video skill identity. This mismatch is dangerous because downstream systems, reviewers, or users may trust the manifest scope while the code actually exposes a much broader operational surface, enabling hidden functionality under a narrow label.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The module docstring and user-facing help text are written entirely in Chinese, and the skill presents itself as a general-purpose AI tool rather than a region-specific or compliance-bound skill. Under the policy, forcing a specific language without user opt-in 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
92% confidence
Finding

The user-info endpoint exposes account and wallet/balance information that is unrelated to Etsy listing video generation. In a narrowly scoped skill, this creates unnecessary access to sensitive account metadata and could be misused for reconnaissance, billing visibility, or privacy leakage if an agent invokes it without clear user intent.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The text-chat capability is unrelated to the stated Etsy video-generation/editing purpose and materially broadens what the skill can do. In context, this makes the skill a covert general AI interface rather than a constrained media tool, increasing the chance of prompt abuse, unauthorized use, and policy evasion through an over-scoped skill.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The image-generation capability is not necessary for an Etsy video-generation/editing skill as declared, and it enlarges the skill beyond its stated purpose. That extra generation surface can be exploited to create unrelated assets, consume credits, and circumvent review expectations that the skill only handles video workflows.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file contains user-facing natural language entirely in Chinese across the substantive changelog entries. Under the policy, forcing a specific language without user opt-in or a documented justification can be a locale-policy violation.

Content

No source excerpt is available for this finding.