The Agent Skills Directory

[DATA_EXPOSURE]: The skill instructions direct the agent to scan sensitive local directories and files to aggregate system data for visualization. Evidence includes:
Scanning ~/Coding/skills/ for installed components.
Accessing BUSINESS_CONTEXT.md and README.md files which may contain sensitive business logic or internal descriptions.
Accessing "Recent task / chat history if accessible," which exposes the content of previous user interactions.
[COMMAND_EXECUTION]: To gather the necessary data for the diagram, the agent must perform broad directory listings and file read operations across the file system.
[PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) because it ingests and processes data from external, potentially untrusted sources.
Ingestion points: Reads content from BUSINESS_CONTEXT.md, README.md, and recent chat/task history.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' warnings for the data being ingested.
Capability inventory: The skill has the capability to read files, scan directories, and write output to both HTML and Markdown files.
Sanitization: There are no instructions provided for sanitizing or escaping the content gathered from project files before it is processed or rendered into the HTML diagram.

workflow-visualizer