The Agent Skills Directory

[Indirect Prompt Injection] (LOW): The skill analyzes local source code, which creates a surface for indirect prompt injection if project files contain adversarial instructions.
Ingestion points: The skill utilizes read_file and grep_search to ingest content from the project's source directory (e.g., **/domain/**/*.py).
Boundary markers: Absent; there are no instructions provided to the agent to treat ingested file content as untrusted data or to ignore embedded instructions.
Capability inventory: The create_file tool allows the agent to write to the file system, meaning an injection could potentially trick the agent into creating malicious code or backdoors.
Sanitization: Absent; the skill performs no validation or sanitization of the content it reads before processing it.

ddd-architect