The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data (existing source code, tests, and repository conventions) and execute test suites as part of the TDD cycle. This combination of reading potentially untrusted data and possessing execution capabilities creates a surface for indirect prompt injection, where malicious instructions embedded in code comments or data files could attempt to influence the agent's behavior.
Ingestion points: The skill reads the public surface of the code, callers, existing tests, and repository conventions as specified in SKILL.md and references/test-first.md.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands in comments are provided in the skill instructions.
Capability inventory: The skill instructs the agent to 'Run focused checks and the relevant suite' as described in SKILL.md.
Sanitization: There are no explicit instructions for sanitizing or escaping content read from files before processing.

tdd