interior-architectural-scene-planner

Pass

Audited by Gen Agent Trust Hub on Nov 2, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of Markdown documentation and reference files. It does not contain any executable scripts (Python, JavaScript, Shell) or configuration files that trigger code execution.
  • [SAFE]: No obfuscation techniques such as Base64 encoding, zero-width characters, or homoglyphs were detected in the instructions or reference materials.
  • [SAFE]: The skill does not perform any network operations, data exfiltration, or external downloads. All referenced resources are internal markdown files.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes an external "brief" from an upstream agent. While this is a data ingestion point, the skill's capabilities are limited to emitting structured text plans for downstream planners and it has no access to sensitive system resources, file writing, or network operations, posing no significant risk.
  • Ingestion points: Reads scene briefs from the intent-to-3d-brief-writer skill.
  • Boundary markers: None present; the skill treats the brief as raw instructional input.
  • Capability inventory: Limited to text output generation; no shell execution, file system writes, or network operations.
  • Sanitization: None; the skill relies on internal logic to validate dimensions and style consistency against its own reference rules.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 2, 2026, 07:51 AM