测试FFmpeg功能
AI agents invoke test_ffmpeg_functionality to trigger actions in Auto Video Generator. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Testing FFmpeg functionality involves executing the FFmpeg binary/library to verify its capabilities. This triggers external process execution whose effects depend on the test arguments passed. It is not a pure read/query operation, but rather an active execution of a system-level tool. Severity is medium as test runs are typically scoped but could still consume resources or interact with the filesystem.
From the tool's definition '测试FFmpeg功能' (Test FFmpeg functionality) — invokes FFmpeg, an external media processing engine, to run test operations
Attacks that exploit this kind of access
测试FFmpeg功能. It is categorised as a Execute tool in the Auto Video Generator MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Auto Video Generator MCP server in PolicyLayer and add a rule for test_ffmpeg_functionality: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Auto Video Generator. Nothing to install.
test_ffmpeg_functionality is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the test_ffmpeg_functionality rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for test_ffmpeg_functionality. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
test_ffmpeg_functionality is provided by the Auto Video Generator MCP server (zgmurder/auto_video_generator-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →