autopilot-pane-control

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill consists entirely of Markdown documentation and YAML metadata. No executable scripts, binaries, or package manager configuration files were found.
  • [SAFE]: The tools referenced (openagents.pane.* and openagents.cad.*) are legitimate vendor resources belonging to the author 'openagentsinc'. No malicious activity or unauthorized data access was detected.
  • [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection through the natural language prompt field in the openagents.cad.intent tool. [Ingestion points]: User-provided strings in the intent tool prompt. [Boundary markers]: None identified in the provided documentation. [Capability inventory]: Desktop UI management and CAD state manipulation. [Sanitization]: No sanitization or validation methods are described.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 11:11 PM