The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and follow instructions from external local files, creating a theoretical surface for indirect prompt injection if those files contain malicious instructions.
Ingestion points: SKILL.md (references to ../testing-standard/SKILL.md and references/local-conventions.md).
Boundary markers: Absent; the agent is instructed to treat the content of these files as the "canonical testing policy."
Capability inventory: Reading and reporting on repository files and testing configurations.
Sanitization: None; the instructions are adopted directly as policy guidelines.

test-strategy