mux-video
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation, API references, and specs from official Mux domains (mux.com) and the vendor's GitHub repository (github.com/muxinc). These resources provide the LLM with up-to-date context directly from the service provider.
- [COMMAND_EXECUTION]: The instructions direct the agent to utilize the Mux CLI tool (
mux docs find) if it is installed on the system to efficiently search for documentation pages without loading entire indexes into the context. - [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection because it ingests external documentation content to formulate responses.
- Ingestion points: Markdown documentation files and text-based collection indexes are retrieved from external URLs defined in
SKILL.md(e.g.,https://www.mux.com/docs/core.txt). - Boundary markers: The workflow instructs the agent to answer specifically from the fetched content and cite the source, though it does not explicitly define unique delimiters to isolate the documentation from the prompt.
- Capability inventory: The skill can execute
muxCLI commands via the shell. - Sanitization: There is no explicit sanitization or filtering of the fetched markdown text before it is processed by the agent.
Audit Metadata