threejs-debug-profiler
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves ingesting and analyzing untrusted external data, such as Three.js project source code, asset files, and browser console/network logs.
- Ingestion points: The agent is instructed to read console errors, inspect files in
public/directories, and evaluate imported asset paths as part of the triage and debugging workflow defined inSKILL.mdandreferences/debug-profile-checklists.md. - Boundary markers: The instructions do not specify the use of delimiters or specific warnings to ignore instructions embedded within the processed game code or logs.
- Capability inventory: The skill requires the agent to modify project files to fix root causes and execute terminal commands to reproduce issues and verify fixes.
- Sanitization: There are no explicit instructions for sanitizing or filtering instructions that might be present in the user-provided code or error logs.
Audit Metadata