specialist-game-development-blender-blender-addon-engineer

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill interpolates the user's input variable directly into a subagent prompt, which could allow a malicious user to influence or override the subagent's intended behavior through the input data.
  • Ingestion points: The {the user's question} variable within the Agent tool call in SKILL.md accepts untrusted data.
  • Boundary markers: None (the variable is not wrapped in delimiters or accompanied by instructions to ignore embedded commands).
  • Capability inventory: The skill utilizes the Agent tool to spawn subagents, which potentially grants the subagent access to other platform capabilities.
  • Sanitization: No input sanitization or validation is applied to the user input before it is used in the prompt template.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:50 PM
Security Audit — agent-trust-hub — specialist-game-development-blender-blender-addon-engineer