The Agent Skills Directory

[Indirect Prompt Injection] (LOW): The skill ingests data from untrusted local files, creating a surface for indirect prompt injection where instructions hidden in the documentation could influence the agent's behavior. • Ingestion points: The skill reads content from README.md, lazyworktree.1, and internal/app/screen/help.go. • Boundary markers: Absent; there are no instructions to the agent to disregard instructions found within the files. • Capability inventory: The skill uses a Read tool to access files but does not have write or execute capabilities. • Sanitization: None; the content is read and processed directly as text.

doc-sync