claim-diagram-card
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using
magick(ImageMagick) to resize, strip metadata, and compress generated images. - [DYNAMIC_EXECUTION]: The skill uses dynamically generated bash commands to perform image optimization, specifically calling
magickwith arguments that may include descriptive filenames derived from note content. - [INDIRECT_PROMPT_INJECTION]: The skill reads external data from wiki claim notes to generate both ASCII diagrams and prompts for an image generator, creating a vulnerability surface.
- Ingestion points: Reads target
wiki/* — Claim*.mdnotes to identify mechanisms for diagramming. - Boundary markers: None; the instructions do not provide delimiters or instructions to ignore embedded commands within the notes.
- Capability inventory: Shell command execution (
magick,ls), file system writes towiki/and_media/directories, and note modification. - Sanitization: No sanitization is specified for the content extracted from notes before it is passed to the image generation tool or the shell environment.
Audit Metadata