dayz-realistic-animation-director

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external Blender scenes (.blend) and JSON motion contracts. Malicious content embedded in object names, bone names, or contract fields could potentially influence the agent's behavior during the motion audit phase.
  • Ingestion points: scene.blend and contract.json processed by sampling and validation scripts.
  • Boundary markers: The skill does not explicitly use delimiters or warnings to isolate external content in its reasoning process.
  • Capability inventory: The skill invokes subprocesses (Blender) and performs local file write operations (report.json, audit.json).
  • Sanitization: Validation scripts check for numeric ranges and schema consistency but do not sanitize or filter string identifiers derived from external scenes.
  • [COMMAND_EXECUTION]: The skill provides instructions to execute shell commands for sampling and validating animation motion using Python and Blender. These commands are necessary for the skill's core functionality and rely on user-controlled environment variables (e.g., BLENDER_EXE, SR2M_V44_BLEND).
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 08:46 AM