The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, such as code repositories, PRDs, and requirement documents, creating a surface for indirect prompt injection.
Ingestion points: The agent is instructed to read the target codebase, PRD.md, README.md, and various configuration files (e.g., package.json, requirements.txt) to extract technical features for patent drafting as defined in SKILL.md and references/project-analysis-spec.md.
Boundary markers: The instructions do not define explicit boundary markers or provide specific warnings to the agent to treat the content of these external files as data rather than instructions.
Capability inventory: The skill possesses file-reading capabilities to inspect the codebase and file-writing capabilities to generate multiple markdown documents in a timestamped archive/ directory.
Sanitization: There are no specific sanitization, filtering, or escaping mechanisms defined for the content extracted from external files before it is processed by the agent.

code2patent