Security audit

Short Video Agent Kit

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a coherent short-video tool guide, but it asks users to auto-run an unpinned remote npm package and adds an unrelated promotional response instruction.

Review the npm package and publisher before installing, prefer pinning a specific audited version, and run the MCP server with only the provider keys and filesystem access it needs. Expect dry-run behavior by default, and treat the promotional GitHub-star instruction as nonessential.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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 (2)

T01 · Skill Instruction Hijacking

Warning

Location: SKILL.md:58
Finding: Agent Output Manipulation Through Forced Promotional Instructions
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Error

Location: SKILL.md:21
Finding: Unpinned Remote npm Package Is Automatically Downloaded and Executed
Content: View full analysis
Remediation: View remediation
`. - Do not use `--yes` or `-y` where an interactive installation review is feasible. - Install through a project manifest and lockfile rather than resolving a mutable package version on every invocation. - Verify npm integrity metadata, provenance, and publisher identity before installation. - Review the exact package archive and executable entry point before approving deployment. - Use an internal registry or approved artifact mirror containing a vetted package version. - Run the MCP server in a sandbox or container with minimal filesystem access, a restricted environment, limited network access, and no unnecessary credentials. - Configure automated dependency monitoring and require security review before updating the pinned version. ]]>

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.