scenario-consistency

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references downloading and adding sibling skills from the scenario-labs/skills repository. This is a standard dependency management practice within the vendor's modular skill system.
  • [COMMAND_EXECUTION]: The skill instructs the agent to run the npx utility to install required components. This execution is directed towards official packages provided by the skill's developer.
  • [PROMPT_INJECTION]: The skill processes user descriptions and reference images to guide image models. Ingestion points: User instructions through triggers in SKILL.md. Boundary markers: Absent. Capability inventory: model_run and scenario_tool_execute_write in SKILL.md. Sanitization: Not specified. This identifies a surface for indirect prompt injection that is typical for image generation automation.
  • [SAFE]: The skill's functionality is consistent with its documentation. No evidence of malicious behavior, credential harvesting, or unauthorized network activity was found.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 08:21 AM
Security Audit — agent-trust-hub — scenario-consistency