The Agent Skills Directory

[SAFE]: The skill consists of instructional markdown files providing guidance on Test-Driven Development, mocking, and test quality. No malicious code, command execution, or data exfiltration patterns were detected.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read local codebase files such as GLOSSARY.md and Architecture Decision Records (ADRs) to align testing vocabulary with the project domain.
Ingestion points: The agent is prompted to read local project-specific documentation files (SKILL.md).
Boundary markers: No specific delimiters or "ignore instructions" warnings are provided for the content of these files.
Capability inventory: The agent retains its standard file-read/write and command execution capabilities while following these instructions.
Sanitization: No explicit sanitization of the documentation content is requested, as these are typically trusted project files.
[CREDENTIALS_UNSAFE]: The mocking.md file mentions STRIPE_KEY within a process.env context in an example illustrating poor mockability. This is an instructional reference to standard environment variable usage and does not contain or request the exposure of actual secrets.

tdd