threenix-add-fast-text
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill parses untrusted data from the user's target repository to determine how to integrate the component.
- Ingestion points: Reads repository instructions and inspects package manifests, renderer configurations, and scene composition (SKILL.md Step 1).
- Boundary markers: No explicit markers are used to differentiate between legitimate project code and potentially malicious instructions embedded in the analyzed repository.
- Capability inventory: The skill possesses the ability to write files (Step 4), install packages (Step 6), and execute build commands (Step 7).
- Sanitization: There is no evidence of sanitization or filtering of the content read from the target project.
- [COMMAND_EXECUTION]: The skill triggers the execution of shell commands for type-checking or building the project (Step 7). While intended for validation, this provides a mechanism for shell-level activity.
- [EXTERNAL_DOWNLOADS]: The agent is instructed to fetch component source code and integration metadata from the 'threenix' MCP server. It also performs package installation for any missing dependencies identified by the tool (Step 6).
- [DYNAMIC_EXECUTION]: The skill dynamically generates files by writing content retrieved from the external tool directly to the file system, including decoding Base64 payloads into executable source code (Step 4).
Audit Metadata