The Agent Skills Directory

[NO_CODE]: The skill consists purely of markdown instructions and does not include any external scripts, binaries, or executable code.
[INDIRECT_PROMPT_INJECTION]: The skill interacts with user input and project files to provide test automation guidance, which represents a standard surface for indirect prompt injection.
Ingestion points: User prompts and local project files accessed via Read and Grep tools as specified in SKILL.md.
Boundary markers: No specific boundary markers or 'ignore' instructions are present in SKILL.md to protect against embedded commands in processed data.
Capability inventory: The skill is configured in SKILL.md to allow the agent to use Read, Write, Edit, and Bash tools.
Sanitization: The instructions do not define any specific sanitization or validation procedures for external data.

test-retry-config