The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill requires the agent to analyze the user's codebase to identify components, containers, and relationships for diagram generation. This involves ingesting untrusted data which could potentially contain malicious instructions.
Ingestion points: The 'Analyze codebase' workflow step in SKILL.md and README.md requires the agent to read project files.
Boundary markers: The instructions do not explicitly define boundary markers or instruct the agent to ignore instructions embedded within the codebase being analyzed.
Capability inventory: The skill uses the agent's capabilities to read files and write documentation to the docs/architecture/ directory.
Sanitization: There are no specific instructions for sanitizing or escaping content retrieved from the codebase before it is incorporated into the documentation process.

c4-architecture