threenix-add-camera-controls
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is instructed to ingest data from untrusted sources which creates an attack surface for indirect prompt injection.
- Ingestion points: The agent reads the target repository's instructions, package manager files, and scene composition (SKILL.md, Step 1).
- Boundary markers: None identified. The instructions do not specify using delimiters or warnings to ignore instructions embedded in the project files.
- Capability inventory: The skill has the ability to call the
get_component_referenceMCP tool, write files to the local filesystem (Step 4), install packages (Step 6), and execute build/type-check commands (Step 7). - Sanitization: No sanitization or validation steps are mentioned for the content read from the project repository.
- [EXTERNAL_DOWNLOADS]: The skill uses the
threenixMCP server to fetch external component code and dependency information (Step 3). While these are vendor resources associated with the skill, they represent the retrieval of external data that is subsequently written to the local filesystem. - [COMMAND_EXECUTION]: The skill performs active operations on the host environment based on data retrieved from the remote MCP server.
- Package Installation: Executes commands to install missing dependencies using the project's existing package manager (Step 6).
- Build Execution: Runs type-checks or build commands covering the edited files (Step 7).
Audit Metadata