Back to skill

Security audit

淘宝 电商视频生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its stated video-generation purpose, but it can send the user's AI Hive API key to any configured base URL without validation.

Install only if you trust the AI Hive service and the skill publisher. Use a dedicated API key, avoid setting `AI_HIVE_BASE_URL` or `--base-url` unless you fully trust that endpoint, and consider installing dependencies in a virtual 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:79
Finding

Unpinned Third-Party Dependency Installation

Content
View full analysis
Remediation
View remediation
--hash=sha256: ``` Install it with: ```bash python3 -m pip install --require-hashes -r requirements.txt ``` 4. Document the expected trusted package index and avoid untrusted mirrors. 5. Run dependency vulnerability and provenance checks as part of release preparation. 6. Recommend installation inside a dedicated virtual environment under a non-privileged account. ]]>

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/videogen.py:91
Finding

Bearer API Credential Can Be Forwarded to an Arbitrary Configured Endpoint

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file contains substantive user-facing natural language almost entirely in Chinese, but does not indicate that the skill is Chinese-only or provide any user opt-in for language/locale. Under the policy, forcing a specific language without user choice can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill invokes a Python script with network, shell, file, and environment access but does not declare any explicit tool scope or permission boundaries. This creates an avoidable trust gap: an agent may grant broader execution privileges than necessary, increasing the blast radius if the script, its inputs, or downstream dependencies are abused.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The file implements a broad AI Hive client with text chat, image generation, model enumeration, user info, media upload, and task polling capabilities, while the declared skill purpose is narrowly scoped to ecommerce video generation/editing. This scope expansion increases attack surface and enables unintended actions if the skill is invoked or repurposed outside its advertised function, violating least-privilege expectations for skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This code file contains natural-language strings and descriptions entirely in Chinese, including the module docstring and CLI help text, while the skill is presented as a general-purpose tool rather than a region-specific compliance skill. Under the policy, forcing a specific language without user opt-in is a locale-policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The placeholder value contains the instruction '请替换为你的APIKey' ('please replace with your API key') only in Chinese. This imposes a specific language in user-facing natural-language content without opt-in or justification, which matches the policy category for language or locale violations.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill-facing parser exposes standalone task querying and arbitrary media upload operations that are not part of the manifest-described user capability. While not directly code-execution, these extra operations can be abused for unintended data movement, persistence of user-provided files to remote storage, and expanded API interaction beyond the expected video-generation flow.

Content

No source excerpt is available for this finding.