The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses local shell commands to detect the existence of configuration files in the environment.
Evidence: SKILL.md instructs the agent to execute test -f .baoyu-skills/baoyu-infographic/EXTEND.md and test -f "$HOME/.baoyu-skills/baoyu-infographic/EXTEND.md" to locate optional user preference files.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by incorporating unvetted user content into prompts for downstream image generation tools.
Ingestion points: Source content is ingested from user-provided file paths or manual text entry in Step 1.2 and saved to source.md.
Boundary markers: The skill uses template placeholders like {{CONTENT}} and {{TEXT_LABELS}} in references/base-prompt.md to delimit user content from instructions.
Capability inventory: The skill performs file reading, file writing (e.g., analysis.md, prompts/infographic.md), and invokes other image generation skills.
Sanitization: No explicit sanitization or character escaping of the source content is documented; the skill follows a principle of verbatim data preservation which allows arbitrary text to be passed to the prompt generator.

baoyu-infographic