define-character
Warn
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
magickutility to process images using variables derived from repository files.- Evidence: TheRecompose assemblysection inSKILL.mdcontains shell commands that interpolate variables such as<character>,<left padding>,<cell width>, and<appearance>intomagickcalls.- Risk: If the source files (docs/game/assets.mdordocs/game/world.md) are modified by an attacker to include shell metacharacters, it could lead to arbitrary command execution.- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection.- Ingestion points:docs/game/world.md,docs/game/assets.md,docs/game/story.md, anddocs/game/screenplay.md(referenced inSKILL.md).- Boundary markers: Absent. The skill instructions direct the agent to quote entire sections like## Visual directiondirectly into generation prompts.- Capability inventory: The agent has the ability to execute shell commands (magick) and write to the source code directory (src/).- Sanitization: No sanitization or validation of the ingested markdown content is performed before processing.- [EXTERNAL_DOWNLOADS]: The skill relies on external binary tools and project-level dependencies.- Evidence: The instructions requireImageMagick 7to be installed and reference documentation and recipes within thefondalepackage undernode_modules.- Note: While these are standard requirements for the stated purpose, they represent a dependency on external code and environment configuration.
Audit Metadata