skills/ckokoski/authoragent/outline/Gen Agent Trust Hub

outline

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-supplied story data to create structured outlines, presenting an indirect prompt injection surface.
  • Ingestion points: The agent ingests user-provided creative content, plot beats, and story descriptions through natural language interaction.
  • Boundary markers: The instructions lack explicit boundary markers or directives for the agent to disregard potential instructions embedded within the processed story data.
  • Capability inventory: The skill utilizes file:write permissions to save the generated outlines to the project's directory.
  • Sanitization: There is no evidence of input validation or content filtering implemented prior to writing the user-influenced content to the filesystem.
  • [NO_CODE]: The skill consists entirely of natural language instructions and configuration without any accompanying executable scripts or binaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 07:41 PM
Security Audit — agent-trust-hub — outline