runware-prompting

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a guide for prompting different AI model families. It consists entirely of natural language instructions and documentation.
  • [NO_CODE]: No scripts, binaries, or executable commands are included in the skill configuration or instructions.
  • [PROMPT_INJECTION]: There are no attempts to override agent behavior, bypass safety filters, or extract system prompts. The instructions are focused on cinematic grammar and structured prompting techniques.
  • [DATA_EXFILTRATION]: The skill does not access sensitive files, environment variables, or credentials, nor does it perform any network operations.
  • [REMOTE_CODE_EXECUTION]: No patterns for downloading or executing external scripts or packages were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 04:08 PM
Security Audit — agent-trust-hub — runware-prompting