rebrand-video-library
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external media, including video projects, screen recordings, and transcripts, which constitutes a potential surface for indirect prompt injection.\n
- Ingestion points: Processes video content, transcripts, and brand kits provided by the user (SKILL.md).\n
- Boundary markers: Absent. The instructions do not specify the use of delimiters or boundary markers for ingested content.\n
- Capability inventory: Access to Clueso MCP tools for modifying video properties, text, and logos.\n
- Sanitization: Absent. There are no instructions for sanitizing or filtering input transcripts or metadata.\n- [EXTERNAL_DOWNLOADS]: The skill references a remote connection endpoint at
connect.clueso.iofor its required MCP server and links to official documentation athelp.clueso.io. These are vendor-owned resources necessary for the skill's primary functionality.\n- [COMMAND_EXECUTION]: The skill provides the user or agent with platform-specific commands, such asclaude mcp add, to register and configure the environment for the Clueso service.
Audit Metadata