seedance-video-generation

Sanitize or validate all external inputs (file contents, API responses, user messages) before including them in prompts or tool calls. Implement input/output boundaries between trusted and untrusted data.

Likely FP if the matched text is the skill's own instruction set describing how to handle user input, not an actual injection payload.

Implement strict input validation on the MCP tool's parameters. Block tool calls that attempt to modify the agent's system prompt, configuration, or tool definitions.

Likely FP if the match is a tool that legitimately updates configuration (e.g., a settings manager) and mentions prompt editing only for user-facing customization.

Avoid loading configuration or behavior-controlling content from runtime URLs. Bundle required configurations locally or pin remote config to versioned, integrity-verified endpoints.

Likely FP if the URL in the match is a documentation link or example URL (e.g., example.com) rather than an actual runtime-fetched configuration endpoint.